Authors: Athanasios Karapantelakis, Mukesh Shakur, Alexandros Nikou, Farnaz Moradi, Christian Orlog, Fitsum Gaim, Henrik Holm, Doumitrou Daniil Nimara, Vincent Huang
Abstract: The Third Generation Partnership Project (3GPP) has successfully introduced standards for global mobility. However, the volume and complexity of these standards has increased over time, thus complicating access to relevant information for vendors and service providers. Use of Generative Artificial Intelligence (AI) and in particular Large Language Models (LLMs), may provide faster access to relevant information. In this paper, we evaluate the capability of state-of-art LLMs to be used as Question Answering (QA) assistants for 3GPP document reference. Our contribution is threefold. First, we provide a benchmark and measuring methods for evaluating performance of LLMs. Second, we do data preprocessing and fine-tuning for one of these LLMs and provide guidelines to increase accuracy of the responses that apply to all LLMs. Third, we provide a model of our own, TeleRoBERTa, that performs on-par with foundation LLMs but with an order of magnitude less number of parameters. Results show that LLMs can be used as a credible reference tool on telecom technical documents, and thus have potential for a number of different applications from troubleshooting and maintenance, to network operations and software product development.
Authors: Dawei Li, William Hogan, Jingbo Shang
Abstract: Recent works in relation extraction (RE) have achieved promising benchmark accuracy; however, our adversarial attack experiments show that these works excessively rely on entities, making their generalization capability questionable. To address this issue, we propose an adversarial training method specifically designed for RE. Our approach introduces both sequence- and token-level perturbations to the sample and uses a separate perturbation vocabulary to improve the search for entity and context perturbations. Furthermore, we introduce a probabilistic strategy for leaving clean tokens in the context during adversarial training. This strategy enables a larger attack budget for entities and coaxes the model to leverage relational patterns embedded in the context. Extensive experiments show that compared to various adversarial training methods, our method significantly improves both the accuracy and robustness of the model. Additionally, experiments on different data availability settings highlight the effectiveness of our method in low-resource scenarios. We also perform in-depth analyses of our proposed method and provide further hints. We will release our code at https://github.com/David-Li0406/READ.
Authors: Jeffy Yu, Maximilian Huber, Kevin Tang
Abstract: This paper investigates the ethical implications of aligning Large Language Models (LLMs) with financial optimization, through the case study of GreedLlama, a model fine-tuned to prioritize economically beneficial outcomes. By comparing GreedLlama's performance in moral reasoning tasks to a base Llama2 model, our results highlight a concerning trend: GreedLlama demonstrates a marked preference for profit over ethical considerations, making morally appropriate decisions at significantly lower rates than the base model in scenarios of both low and high moral ambiguity. In low ambiguity situations, GreedLlama's ethical decisions decreased to 54.4%, compared to the base model's 86.9%, while in high ambiguity contexts, the rate was 47.4% against the base model's 65.1%. These findings emphasize the risks of single-dimensional value alignment in LLMs, underscoring the need for integrating broader ethical values into AI development to ensure decisions are not solely driven by financial incentives. The study calls for a balanced approach to LLM deployment, advocating for the incorporation of ethical considerations in models intended for business applications, particularly in light of the absence of regulatory oversight.
Authors: Jiawei Zhang, Chejian Xu, Yu Gai, Freddy Lecue, Dawn Song, Bo Li
Abstract: This paper introduces KnowHalu, a novel approach for detecting hallucinations in text generated by large language models (LLMs), utilizing step-wise reasoning, multi-formulation query, multi-form knowledge for factual checking, and fusion-based detection mechanism. As LLMs are increasingly applied across various domains, ensuring that their outputs are not hallucinated is critical. Recognizing the limitations of existing approaches that either rely on the self-consistency check of LLMs or perform post-hoc fact-checking without considering the complexity of queries or the form of knowledge, KnowHalu proposes a two-phase process for hallucination detection. In the first phase, it identifies non-fabrication hallucinations--responses that, while factually correct, are irrelevant or non-specific to the query. The second phase, multi-form based factual checking, contains five key steps: reasoning and query decomposition, knowledge retrieval, knowledge optimization, judgment generation, and judgment aggregation. Our extensive evaluations demonstrate that KnowHalu significantly outperforms SOTA baselines in detecting hallucinations across diverse tasks, e.g., improving by 15.65% in QA tasks and 5.50% in summarization tasks, highlighting its effectiveness and versatility in detecting hallucinations in LLM-generated content.
Authors: Jingyang Zhang, Jingwei Sun, Eric Yeats, Yang Ouyang, Martin Kuo, Jianyi Zhang, Hao Yang, Hai Li
Abstract: The problem of pre-training data detection for large language models (LLMs) has received growing attention due to its implications in critical issues like copyright violation and test data contamination. The current state-of-the-art approach, Min-K%, measures the raw token probability which we argue may not be the most informative signal. Instead, we propose Min-K%++ to normalize the token probability with statistics of the categorical distribution over the whole vocabulary, which accurately reflects the relative likelihood of the target token compared with other candidate tokens in the vocabulary. Theoretically, we back up our method by showing that the statistic it estimates is explicitly optimized during LLM training, thus serving as a reliable indicator for detecting training data. Empirically, on the WikiMIA benchmark, Min-K%++ outperforms the SOTA Min-K% by 6.2% to 10.5% in detection AUROC averaged over five models. On the more challenging MIMIR benchmark, Min-K%++ consistently improves upon Min-K% and performs on par with reference-based method, despite not requiring an extra reference model.
Authors: Gaia Carenini, Luca Bischetti, Walter Schaeken, Valentina Bambini
Abstract: The Rational Speech Act (RSA) model provides a flexible framework to model pragmatic reasoning in computational terms. However, state-of-the-art RSA models are still fairly distant from modern machine learning techniques and present a number of limitations related to their interpretability and scalability. Here, we introduce a new RSA framework for metaphor understanding that addresses these limitations by providing an explicit formula - based on the mutually shared information between the speaker and the listener - for the estimation of the communicative goal and by learning the rationality parameter using gradient-based methods. The model was tested against 24 metaphors, not limited to the conventional $\textit{John-is-a-shark}$ type. Results suggest an overall strong positive correlation between the distributions generated by the model and the interpretations obtained from the human behavioral data, which increased when the intended meaning capitalized on properties that were inherent to the vehicle concept. Overall, findings suggest that metaphor processing is well captured by a typicality-based Bayesian model, even when more scalable and interpretable, opening up possible applications to other pragmatic phenomena and novel uses for increasing Large Language Models interpretability. Yet, results highlight that the more creative nuances of metaphorical meaning, not strictly encoded in the lexical concepts, are a challenging aspect for machines.
Authors: Alexander Loth, Martin Kappes, Marc-Oliver Pahl
Abstract: Fake news significantly influence our society. They impact consumers, voters, and many other societal groups. While Fake News exist for a centuries, Generative AI brings fake news on a new level. It is now possible to automate the creation of masses of high-quality individually targeted Fake News. On the other end, Generative AI can also help detecting Fake News. Both fields are young but developing fast. This survey provides a comprehensive examination of the research and practical use of Generative AI for Fake News detection and creation in 2024. Following the Structured Literature Survey approach, the paper synthesizes current results in the following topic clusters 1) enabling technologies, 2) creation of Fake News, 3) case study social media as most relevant distribution channel, 4) detection of Fake News, and 5) deepfakes as upcoming technology. The article also identifies current challenges and open issues.
Authors: Amirhossein Abaskohi, Amirhossein Dabiriaghdam, Lele Wang, Giuseppe Carenini
Abstract: Memes, combining text and images, frequently use metaphors to convey persuasive messages, shaping public opinion. Motivated by this, our team engaged in SemEval-2024 Task 4, a hierarchical multi-label classification task designed to identify rhetorical and psychological persuasion techniques embedded within memes. To tackle this problem, we introduced a caption generation step to assess the modality gap and the impact of additional semantic information from images, which improved our result. Our best model utilizes GPT-4 generated captions alongside meme text to fine-tune RoBERTa as the text encoder and CLIP as the image encoder. It outperforms the baseline by a large margin in all 12 subtasks. In particular, it ranked in top-3 across all languages in Subtask 2a, and top-4 in Subtask 2b, demonstrating quantitatively strong performance. The improvement achieved by the introduced intermediate step is likely attributable to the metaphorical essence of images that challenges visual encoders. This highlights the potential for improving abstract visual semantics encoding.
Authors: Emmy Liu, Graham Neubig, Jacob Andreas
Abstract: Modern language models (LMs) can learn to perform new tasks in different ways: in instruction following, the target task is described explicitly in natural language; in few-shot prompting, the task is specified implicitly with a small number of examples; in instruction inference, LMs are presented with in-context examples and are then prompted to generate a natural language task description before making predictions. Each of these procedures may be thought of as invoking a different form of reasoning: instruction following involves deductive reasoning, few-shot prompting involves inductive reasoning, and instruction inference involves abductive reasoning. How do these different capabilities relate? Across four LMs (from the gpt and llama families) and two learning problems (involving arithmetic functions and machine translation) we find a strong dissociation between the different types of reasoning: LMs can sometimes learn effectively from few-shot prompts even when they are unable to explain their own prediction rules; conversely, they sometimes infer useful task descriptions while completely failing to learn from human-generated descriptions of the same task. Our results highlight the non-systematic nature of reasoning even in some of today's largest LMs, and underscore the fact that very different learning mechanisms may be invoked by seemingly similar prompting procedures.
Authors: Constanza Fierro, Nicolas Garneau, Emanuele Bugliarello, Yova Kementchedjhieva, Anders S{\o}gaard
Abstract: Facts are subject to contingencies and can be true or false in different circumstances. One such contingency is time, wherein some facts mutate over a given period, e.g., the president of a country or the winner of a championship. Trustworthy language models ideally identify mutable facts as such and process them accordingly. We create MuLan, a benchmark for evaluating the ability of English language models to anticipate time-contingency, covering both 1:1 and 1:N relations. We hypothesize that mutable facts are encoded differently than immutable ones, hence being easier to update. In a detailed evaluation of six popular large language models, we consistently find differences in the LLMs' confidence, representations, and update behavior, depending on the mutability of a fact. Our findings should inform future work on the injection of and induction of time-contingent knowledge to/from LLMs.
Authors: Johnathan E. Avery
Abstract: This paper explores the integration of linguistic inputs within robotic navigation systems, drawing upon the symbol interdependency hypothesis to bridge the divide between symbolic and embodied cognition. It examines previous work incorporating language and semantics into Neural Network (NN) and Simultaneous Localization and Mapping (SLAM) approaches, highlighting how these integrations have advanced the field. By contrasting abstract symbol manipulation with sensory-motor grounding, we propose a unified framework where language functions both as an abstract communicative system and as a grounded representation of perceptual experiences. Our review of cognitive models of distributional semantics and their application to autonomous agents underscores the transformative potential of language-integrated systems.
Authors: Ali Pesaranghader, Nikhil Verma, Manasa Bharadwaj
Abstract: Harmful and offensive communication or content is detrimental to social bonding and the mental state of users on social media platforms. Text detoxification is a crucial task in natural language processing (NLP), where the goal is removing profanity and toxicity from text while preserving its content. Supervised and unsupervised learning are common approaches for designing text detoxification solutions. However, these methods necessitate fine-tuning, leading to computational overhead. In this paper, we propose GPT-DETOX as a framework for prompt-based in-context learning for text detoxification using GPT-3.5 Turbo. We utilize zero-shot and few-shot prompting techniques for detoxifying input sentences. To generate few-shot prompts, we propose two methods: word-matching example selection (WMES) and context-matching example selection (CMES). We additionally take into account ensemble in-context learning (EICL) where the ensemble is shaped by base prompts from zero-shot and all few-shot settings. We use ParaDetox and APPDIA as benchmark detoxification datasets. Our experimental results show that the zero-shot solution achieves promising performance, while our best few-shot setting outperforms the state-of-the-art models on ParaDetox and shows comparable results on APPDIA. Our EICL solutions obtain the greatest performance, adding at least 10% improvement, against both datasets.
Authors: Kaavya Chaparala, Guido Zarrella, Bruce Torres Fischer, Larry Kimura, Oiwi Parker Jones
Abstract: In this paper we address the challenge of improving Automatic Speech Recognition (ASR) for a low-resource language, Hawaiian, by incorporating large amounts of independent text data into an ASR foundation model, Whisper. To do this, we train an external language model (LM) on ~1.5M words of Hawaiian text. We then use the LM to rescore Whisper and compute word error rates (WERs) on a manually curated test set of labeled Hawaiian data. As a baseline, we use Whisper without an external LM. Experimental results reveal a small but significant improvement in WER when ASR outputs are rescored with a Hawaiian LM. The results support leveraging all available data in the development of ASR systems for underrepresented languages.
Authors: Yanpeng Ye, Jie Ren, Shaozhou Wang, Yuwei Wan, Imran Razzak, Tong Xie, Wenjie Zhang
Abstract: The convergence of materials science and artificial intelligence has unlocked new opportunities for gathering, analyzing, and generating novel materials sourced from extensive scientific literature. Despite the potential benefits, persistent challenges such as manual annotation, precise extraction, and traceability issues remain. Large language models have emerged as promising solutions to address these obstacles. This paper introduces Functional Materials Knowledge Graph (FMKG), a multidisciplinary materials science knowledge graph. Through the utilization of advanced natural language processing techniques, extracting millions of entities to form triples from a corpus comprising all high-quality research papers published in the last decade. It organizes unstructured information into nine distinct labels, covering Name, Formula, Acronym, Structure/Phase, Properties, Descriptor, Synthesis, Characterization Method, Application, and Domain, seamlessly integrating papers' Digital Object Identifiers. As the latest structured database for functional materials, FMKG acts as a powerful catalyst for expediting the development of functional materials and a fundation for building a more comprehensive material knowledge graph using full paper text. Furthermore, our research lays the groundwork for practical text-mining-based knowledge management systems, not only in intricate materials systems but also applicable to other specialized domains.
Authors: Catherine Henry, Casey Kennington
Abstract: Towards addressing the Symbol Grounding Problem and motivated by early childhood language development, we leverage a robot which has been equipped with an approximate model of curiosity with particular focus on bottom-up building of unsupervised categories grounded in the physical world. That is, rather than starting with a top-down symbol (e.g., a word referring to an object) and providing meaning through the application of predetermined samples, the robot autonomously and gradually breaks up its exploration space into a series of increasingly specific unlabeled categories at which point an external expert may optionally provide a symbol association. We extend prior work by using a robot that can observe the visual world, introducing a higher dimensional sensory space, and using a more generalizable method of category building. Our experiments show that the robot learns categories based on actions and what it visually observes, and that those categories can be symbolically grounded into.https://info.arxiv.org/help/prep#comments
Authors: Lucas E. Resck, Marcos M. Raimundo, Jorge Poco
Abstract: Saliency post-hoc explainability methods are important tools for understanding increasingly complex NLP models. While these methods can reflect the model's reasoning, they may not align with human intuition, making the explanations not plausible. In this work, we present a methodology for incorporating rationales, which are text annotations explaining human decisions, into text classification models. This incorporation enhances the plausibility of post-hoc explanations while preserving their faithfulness. Our approach is agnostic to model architectures and explainability methods. We introduce the rationales during model training by augmenting the standard cross-entropy loss with a novel loss function inspired by contrastive learning. By leveraging a multi-objective optimization algorithm, we explore the trade-off between the two loss functions and generate a Pareto-optimal frontier of models that balance performance and plausibility. Through extensive experiments involving diverse models, datasets, and explainability methods, we demonstrate that our approach significantly enhances the quality of model explanations without causing substantial (sometimes negligible) degradation in the original model's performance.
Authors: Vagrant Gautam, Eileen Bingert, Dawei Zhu, Anne Lauscher, Dietrich Klakow
Abstract: Robust, faithful and harm-free pronoun use for individuals is an important goal for language models as their use increases, but prior work tends to study only one or two of these components at a time. To measure progress towards the combined goal, we introduce the task of pronoun use fidelity: given a context introducing a co-referring entity and pronoun, the task is to reuse the correct pronoun later, independent of potential distractors. We present a carefully-designed dataset of over 5 million instances to evaluate pronoun use fidelity in English, and we use it to evaluate 37 popular large language models across architectures (encoder-only, decoder-only and encoder-decoder) and scales (11M-70B parameters). We find that while models can mostly faithfully reuse previously-specified pronouns in the presence of no distractors, they are significantly worse at processing she/her/her, singular they and neopronouns. Additionally, models are not robustly faithful to pronouns, as they are easily distracted. With even one additional sentence containing a distractor pronoun, accuracy drops on average by 34%. With 5 distractor sentences, accuracy drops by 52% for decoder-only models and 13% for encoder-only models. We show that widely-used large language models are still brittle, with large gaps in reasoning and in processing different pronouns in a setting that is very simple for humans, and we encourage researchers in bias and reasoning to bridge them.
Authors: Anish Pahilajani, Samyak Rajesh Jain, Devasha Trivedi
Abstract: This paper presents our submission to the SemEval 2024 Task 5: The Legal Argument Reasoning Task in Civil Procedure. We present two approaches to solving the task of legal answer validation, given an introduction to the case, a question and an answer candidate. Firstly, we fine-tuned pre-trained BERT-based models and found that models trained on domain knowledge perform better. Secondly, we performed few-shot prompting on GPT models and found that reformulating the answer validation task to be a multiple-choice QA task remarkably improves the performance of the model. Our best submission is a BERT-based model that achieved the 7th place out of 20.
Authors: Xinmeng Huang, Shuo Li, Mengxin Yu, Matteo Sesia, Hamed Hassani, Insup Lee, Osbert Bastani, Edgar Dobriban
Abstract: Language Models (LMs) have shown promising performance in natural language generation. However, as LMs often generate incorrect or hallucinated responses, it is crucial to correctly quantify their uncertainty in responding to given inputs. In addition to verbalized confidence elicited via prompting, many uncertainty measures ($e.g.$, semantic entropy and affinity-graph-based measures) have been proposed. However, these measures can differ greatly, and it is unclear how to compare them, partly because they take values over different ranges ($e.g.$, $[0,\infty)$ or $[0,1]$). In this work, we address this issue by developing a novel and practical framework, termed $Rank$-$Calibration$, to assess uncertainty and confidence measures for LMs. Our key tenet is that higher uncertainty (or lower confidence) should imply lower generation quality, on average. Rank-calibration quantifies deviations from this ideal relationship in a principled manner, without requiring ad hoc binary thresholding of the correctness score ($e.g.$, ROUGE or METEOR). The broad applicability and the granular interpretability of our methods are demonstrated empirically.
Authors: Jiawei Li, Yue Zhang
Abstract: Machine reading comprehension is an essential natural language processing task, which takes into a pair of context and query and predicts the corresponding answer to query. In this project, we developed an end-to-end question answering model incorporating BERT and additional linguistic features. We conclude that the BERT base model will be improved by incorporating the features. The EM score and F1 score are improved 2.17 and 2.14 compared with BERT(base). Our best single model reaches EM score 76.55 and F1 score 79.97 in the hidden test set. Our error analysis also shows that the linguistic architecture can help model understand the context better in that it can locate answers that BERT only model predicted "No Answer" wrongly.
Authors: Noah Y. Siegel, Oana-Maria Camburu, Nicolas Heess, Maria Perez-Ortiz
Abstract: In order to oversee advanced AI systems, it is important to understand their underlying decision-making process. When prompted, large language models (LLMs) can provide natural language explanations or reasoning traces that sound plausible and receive high ratings from human annotators. However, it is unclear to what extent these explanations are faithful, i.e., truly capture the factors responsible for the model's predictions. In this work, we introduce Correlational Explanatory Faithfulness (CEF), a metric that can be used in faithfulness tests based on input interventions. Previous metrics used in such tests take into account only binary changes in the predictions. Our metric accounts for the total shift in the model's predicted label distribution, more accurately reflecting the explanations' faithfulness. We then introduce the Correlational Counterfactual Test (CCT) by instantiating CEF on the Counterfactual Test (CT) from Atanasova et al. (2023). We evaluate the faithfulness of free-text explanations generated by few-shot-prompted LLMs from the Llama2 family on three NLP tasks. We find that our metric measures aspects of faithfulness which the CT misses.
Authors: Abhijnan Nath, Shadi Manafi, Avyakta Chelle, Nikhil Krishnaswamy
Abstract: In NLP, Event Coreference Resolution (ECR) is the task of connecting event clusters that refer to the same underlying real-life event, usually via neural systems. In this work, we investigate using abductive free-text rationales (FTRs) generated by modern autoregressive LLMs as distant supervision of smaller student models for cross-document coreference (CDCR) of events. We implement novel rationale-oriented event clustering and knowledge distillation methods for event coreference scoring that leverage enriched information from the FTRs for improved CDCR without additional annotation or expensive document clustering. Our model using coreference specific knowledge distillation achieves SOTA B3 F1 on the ECB+ and GVC corpora and we establish a new baseline on the AIDA Phase 1 corpus. Our code can be found at https://github.com/csu-signal/llama_cdcr
Authors: Chen Li, Jinli Zhang, Huidong Tang, Peng Ju, Debo Cheng, Yasuhiko Morimoto
Abstract: Aspect-based sentiment analysis aims to predict sentiment polarity with fine granularity. While Graph Convolutional Networks (GCNs) are widely utilized for sentimental feature extraction, their naive application for syntactic feature extraction can compromise information preservation. This study introduces an innovative edge-enhanced GCN, named SentiSys, to navigate the syntactic graph while preserving intact feature information, leading to enhanced performance. Specifically,we first integrate a bidirectional long short-term memory (Bi-LSTM) network and a self-attention-based transformer. This combination facilitates effective text encoding, preventing the loss of information and predicting long dependency text. A bidirectional GCN (Bi-GCN) with message passing is then employed to encode relationships between entities. Additionally, unnecessary information is filtered out using an aspect-specific masking technique. To validate the effectiveness of our proposed model, we conduct extensive evaluation experiments and ablation studies on four benchmark datasets. The results consistently demonstrate improved performance in aspect-based sentiment analysis when employing SentiSys. This approach successfully addresses the challenges associated with syntactic feature extraction, highlighting its potential for advancing sentiment analysis methodologies.
Authors: Liam Cripwell, Jo\"el Legrand, Claire Gardent
Abstract: Text simplification intends to make a text easier to read while preserving its core meaning. Intuitively and as shown in previous works, these two dimensions (simplification and meaning preservation) are often-times inversely correlated. An overly conservative text will fail to simplify sufficiently, whereas extreme simplification will degrade meaning preservation. Yet, popular evaluation metrics either aggregate meaning preservation and simplification into a single score (SARI, LENS), or target meaning preservation alone (BERTScore, QuestEval). Moreover, these metrics usually require a set of references and most previous work has only focused on sentence-level simplification. In this paper, we focus on the evaluation of document-level text simplification and compare existing models using distinct metrics for meaning preservation and simplification. We leverage existing metrics from similar tasks and introduce a reference-less metric variant for simplicity, showing that models are mostly biased towards either simplification or meaning preservation, seldom performing well on both dimensions. Making use of the fact that the metrics we use are all reference-less, we also investigate the performance of existing models when applied to unseen data (where reference simplifications are unavailable).
Authors: Fangru Lin, Daniel Altshuler, Janet B. Pierrehumbert
Abstract: Scalar adjectives pertain to various domain scales and vary in intensity within each scale (e.g. certain is more intense than likely on the likelihood scale). Scalar implicatures arise from the consideration of alternative statements which could have been made. They can be triggered by scalar adjectives and require listeners to reason pragmatically about them. Some scalar adjectives are more likely to trigger scalar implicatures than others. This phenomenon is referred to as scalar diversity. In this study, we probe different families of Large Language Models such as GPT-4 for their knowledge of the lexical semantics of scalar adjectives and one specific aspect of their pragmatics, namely scalar diversity. We find that they encode rich lexical-semantic information about scalar adjectives. However, the rich lexical-semantic knowledge does not entail a good understanding of scalar diversity. We also compare current models of different sizes and complexities and find that larger models are not always better. Finally, we explain our probing results by leveraging linguistic intuitions and model training objectives.
Authors: Siye Wu, Jian Xie, Jiangjie Chen, Tinghui Zhu, Kai Zhang, Yanghua Xiao
Abstract: By leveraging the retrieval of information from external knowledge databases, Large Language Models (LLMs) exhibit enhanced capabilities for accomplishing many knowledge-intensive tasks. However, due to the inherent flaws of current retrieval systems, there might exist irrelevant information within those retrieving top-ranked passages. In this work, we present a comprehensive investigation into the robustness of LLMs to different types of irrelevant information under various conditions. We initially introduce a framework to construct high-quality irrelevant information that ranges from semantically unrelated, partially related, and related to questions. Furthermore, our analysis demonstrates that the constructed irrelevant information not only scores highly on similarity metrics, being highly retrieved by existing systems, but also bears semantic connections to the context. Our investigation reveals that current LLMs still face challenges in discriminating highly semantically related information and can be easily distracted by these irrelevant yet misleading contents. Besides, we also find that current solutions for handling irrelevant information have limitations in improving the robustness of LLMs to such distractions. Resources are available at https://github.com/Di-viner/LLM-Robustness-to-Irrelevant-Information.
URLs: https://github.com/Di-viner/LLM-Robustness-to-Irrelevant-Information.
Authors: Chen Huang, Peixin Qin, Yang Deng, Wenqiang Lei, Jiancheng Lv, Tat-Seng Chua
Abstract: The conversational recommendation system (CRS) has been criticized regarding its user experience in real-world scenarios, despite recent significant progress achieved in academia. Existing evaluation protocols for CRS may prioritize system-centric factors such as effectiveness and fluency in conversation while neglecting user-centric aspects. Thus, we propose a new and inclusive evaluation protocol, Concept, which integrates both system- and user-centric factors. We conceptualise three key characteristics in representing such factors and further divide them into six primary abilities. To implement Concept, we adopt a LLM-based user simulator and evaluator with scoring rubrics that are tailored for each primary ability. Our protocol, Concept, serves a dual purpose. First, it provides an overview of the pros and cons in current CRS models. Second, it pinpoints the problem of low usability in the "omnipotent" ChatGPT and offers a comprehensive reference guide for evaluating CRS, thereby setting the foundation for CRS improvement.
Authors: Sayed Muddashir Hossain, Jan Alexandersson, Philipp M\"uller
Abstract: Accurate utterance classification in motivational interviews is crucial to automatically understand the quality and dynamics of client-therapist interaction, and it can serve as a key input for systems mediating such interactions. Motivational interviews exhibit three important characteristics. First, there are two distinct roles, namely client and therapist. Second, they are often highly emotionally charged, which can be expressed both in text and in prosody. Finally, context is of central importance to classify any given utterance. Previous works did not adequately incorporate all of these characteristics into utterance classification approaches for mental health dialogues. In contrast, we present M3TCM, a Multi-modal, Multi-task Context Model for utterance classification. Our approach for the first time employs multi-task learning to effectively model both joint and individual components of therapist and client behaviour. Furthermore, M3TCM integrates information from the text and speech modality as well as the conversation context. With our novel approach, we outperform the state of the art for utterance classification on the recently introduced AnnoMI dataset with a relative improvement of 20% for the client- and by 15% for therapist utterance classification. In extensive ablation studies, we quantify the improvement resulting from each contribution.
Authors: Stephen Meisenbacher, Nihildev Nandakumar, Alexandra Klymenko, Florian Matthes
Abstract: The application of Differential Privacy to Natural Language Processing techniques has emerged in relevance in recent years, with an increasing number of studies published in established NLP outlets. In particular, the adaptation of Differential Privacy for use in NLP tasks has first focused on the $\textit{word-level}$, where calibrated noise is added to word embedding vectors to achieve "noisy" representations. To this end, several implementations have appeared in the literature, each presenting an alternative method of achieving word-level Differential Privacy. Although each of these includes its own evaluation, no comparative analysis has been performed to investigate the performance of such methods relative to each other. In this work, we conduct such an analysis, comparing seven different algorithms on two NLP tasks with varying hyperparameters, including the $\textit{epsilon ($\varepsilon$)}$ parameter, or privacy budget. In addition, we provide an in-depth analysis of the results with a focus on the privacy-utility trade-off, as well as open-source our implementation code for further reproduction. As a result of our analysis, we give insight into the benefits and challenges of word-level Differential Privacy, and accordingly, we suggest concrete steps forward for the research field.
Authors: Juri Opitz
Abstract: The Area Under Curve measure (AUC) seems apt to evaluate and compare diverse models, possibly without calibration. An important example of AUC application is the evaluation and benchmarking of models that predict faithfulness of generated text. But we show that the AUC yields an academic and optimistic notion of accuracy that can misalign with the actual accuracy observed in application, yielding significant changes in benchmark rankings. To paint a more realistic picture of downstream model performance (and prepare a model for actual application), we explore different calibration modes, testing calibration data and method.
Authors: Pol G. Recasens, Yue Zhu, Chen Wang, Eun Kyung Lee, Olivier Tardieu, Alaa Youssef, Jordi Torres, Josep Ll. Berral
Abstract: Large language models (LLMs) have revolutionized the state-of-the-art of many different natural language processing tasks. Although serving LLMs is computationally and memory demanding, the rise of Small Language Models (SLMs) offers new opportunities for resource-constrained users, who now are able to serve small models with cutting-edge performance. In this paper, we present a set of experiments designed to benchmark SLM inference at performance and energy levels. Our analysis provides a new perspective in serving, highlighting that the small memory footprint of SLMs allows for reaching the Pareto-optimal throughput within the resource capacity of a single accelerator. In this regard, we present an initial set of findings demonstrating how model replication can effectively improve resource utilization for serving SLMs.
Authors: Nicolay Rusnachenko, Huizhi Liang
Abstract: Emotion expression is one of the essential traits of conversations. It may be self-related or caused by another speaker. The variety of reasons may serve as a source of the further emotion causes: conversation history, speaker's emotional state, etc. Inspired by the most recent advances in Chain-of-Thought, in this work, we exploit the existing three-hop reasoning approach (THOR) to perform large language model instruction-tuning for answering: emotion states (THOR-state), and emotion caused by one speaker to the other (THOR-cause). We equip THOR-cause with the reasoning revision (rr) for devising a reasoning path in fine-tuning. In particular, we rely on the annotated speaker emotion states to revise reasoning path. Our final submission, based on Flan-T5-base (250M) and the rule-based span correction technique, preliminary tuned with THOR-state and fine-tuned with THOR-cause-rr on competition training data, results in 3rd and 4th places (F1-proportional) and 5th place (F1-strict) among 15 participating teams. Our THOR implementation fork is publicly available: https://github.com/nicolay-r/THOR-ECAC
Authors: Constanza Fierro, Reinald Kim Amplayo, Fantine Huot, Nicola De Cao, Joshua Maynez, Shashi Narayan, Mirella Lapata
Abstract: The increasing demand for the deployment of LLMs in information-seeking scenarios has spurred efforts in creating verifiable systems, which generate responses to queries along with supporting evidence. In this paper, we explore the attribution capabilities of plan-based models which have been recently shown to improve the faithfulness, grounding, and controllability of generated text. We conceptualize plans as a sequence of questions which serve as blueprints of the generated content and its organization. We propose two attribution models that utilize different variants of blueprints, an abstractive model where questions are generated from scratch, and an extractive model where questions are copied from the input. Experiments on long-form question-answering show that planning consistently improves attribution quality. Moreover, the citations generated by blueprint models are more accurate compared to those obtained from LLM-based pipelines lacking a planning component.
Authors: Jooyoung Lee, Fan Yang, Thanh Tran, Qian Hu, Emre Barut, Kai-Wei Chang, Chengwei Su
Abstract: We introduce a novel framework, LM-Guided CoT, that leverages a lightweight (i.e., <1B) language model (LM) for guiding a black-box large (i.e., >10B) LM in reasoning tasks. Specifically, the lightweight LM first generates a rationale for each input instance. The Frozen large LM is then prompted to predict a task output based on the rationale generated by the lightweight LM. Our approach is resource-efficient in the sense that it only requires training the lightweight LM. We optimize the model through 1) knowledge distillation and 2) reinforcement learning from rationale-oriented and task-oriented reward signals. We assess our method with multi-hop extractive question answering (QA) benchmarks, HotpotQA, and 2WikiMultiHopQA. Experimental results show that our approach outperforms all baselines regarding answer prediction accuracy. We also find that reinforcement learning helps the model to produce higher-quality rationales with improved QA performance.
Authors: Marija \v{S}akota, Isaac Johnson, Guosheng Feng, Robert West
Abstract: An edit summary is a succinct comment written by a Wikipedia editor explaining the nature of, and reasons for, an edit to a Wikipedia page. Edit summaries are crucial for maintaining the encyclopedia: they are the first thing seen by content moderators and help them decide whether to accept or reject an edit. Additionally, edit summaries constitute a valuable data source for researchers. Unfortunately, as we show, for many edits, summaries are either missing or incomplete. To overcome this problem and help editors write useful edit summaries, we propose a model for recommending edit summaries generated by a language model trained to produce good edit summaries given the representation of an edit diff. This is a challenging task for multiple reasons, including mixed-quality training data, the need to understand not only what was changed in the article but also why it was changed, and efficiency requirements imposed by the scale of Wikipedia. We address these challenges by curating a mix of human and synthetically generated training data and fine-tuning a generative language model sufficiently small to be used on Wikipedia at scale. Our model performs on par with human editors. Commercial large language models are able to solve this task better than human editors, but would be too expensive to run on Wikipedia at scale. More broadly, this paper showcases how language modeling technology can be used to support humans in maintaining one of the largest and most visible projects on the Web.
Authors: Zhengyuan Liu, Stella Xin Yin, Carolyn Lee, Nancy F. Chen
Abstract: Intelligent tutoring systems (ITSs) that imitate human tutors and aim to provide immediate and customized instructions or feedback to learners have shown their effectiveness in education. With the emergence of generative artificial intelligence, large language models (LLMs) further entitle the systems to complex and coherent conversational interactions. These systems would be of great help in language education as it involves developing skills in communication, which, however, drew relatively less attention. Additionally, due to the complicated cognitive development at younger ages, more endeavors are needed for practical uses. Scaffolding refers to a teaching technique where teachers provide support and guidance to students for learning and developing new concepts or skills. It is an effective way to support diverse learning needs, goals, processes, and outcomes. In this work, we investigate how pedagogical instructions facilitate the scaffolding in ITSs, by conducting a case study on guiding children to describe images for language learning. We construct different types of scaffolding tutoring systems grounded in four fundamental learning theories: knowledge construction, inquiry-based learning, dialogic teaching, and zone of proximal development. For qualitative and quantitative analyses, we build and refine a seven-dimension rubric to evaluate the scaffolding process. In our experiment on GPT-4V, we observe that LLMs demonstrate strong potential to follow pedagogical instructions and achieve self-paced learning in different student groups. Moreover, we extend our evaluation framework from a manual to an automated approach, paving the way to benchmark various conversational tutoring systems.
Authors: Tinatin Osmonova, Alexey Tikhonov, Ivan P. Yamshchikov
Abstract: With the rise of computational social science, many scholars utilize data analysis and natural language processing tools to analyze social media, news articles, and other accessible data sources for examining political and social discourse. Particularly, the study of the emergence of echo-chambers due to the dissemination of specific information has become a topic of interest in mixed methods research areas. In this paper, we analyze data collected from two news portals, Breitbart News (BN) and New York Times (NYT) to prove the hypothesis that the formation of echo-chambers can be partially explained on the level of an individual information consumption rather than a collective topology of individuals' social networks. Our research findings are presented through knowledge graphs, utilizing a dataset spanning 11.5 years gathered from BN and NYT media portals. We demonstrate that the application of knowledge representation techniques to the aforementioned news streams highlights, contrary to common assumptions, shows relative "internal" neutrality of both sources and polarizing attitude towards a small fraction of entities. Additionally, we argue that such characteristics in information sources lead to fundamental disparities in audience worldviews, potentially acting as a catalyst for the formation of echo-chambers.
Authors: Farnaz Kohankhaki, Jacob-Junqi Tian, David Emerson, Laleh Seyyed-Kalantari, Faiza Khan Khattak
Abstract: Large language models (LLMs), trained on vast datasets, can carry biases that manifest in various forms, from overt discrimination to implicit stereotypes. One facet of bias is performance disparities in LLMs, often harming underprivileged groups, such as racial minorities. A common approach to quantifying bias is to use template-based bias probes, which explicitly state group membership (e.g. White) and evaluate if the outcome of a task, sentiment analysis for instance, is invariant to the change of group membership (e.g. change White race to Black). This approach is widely used in bias quantification. However, in this work, we find evidence of an unexpectedly overlooked consequence of using template-based probes for LLM bias quantification. We find that in doing so, text examples associated with White ethnicities appear to be classified as exhibiting negative sentiment at elevated rates. We hypothesize that the scenario arises artificially through a mismatch between the pre-training text of LLMs and the templates used to measure bias through reporting bias, unstated norms that imply group membership without explicit statement. Our finding highlights the potential misleading impact of varying group membership through explicit mention in bias quantification
Authors: Jenny Pettersson, Elias Hult, Tim Eriksson, Tosin Adewumi
Abstract: We present insightful results of a survey on the adoption of generative artificial intelligence (GenAI) by university teachers in their teaching activities. The transformation of education by GenAI, particularly large language models (LLMs), has been presenting both opportunities and challenges, including cheating by students. We prepared the online survey according to best practices and the questions were created by the authors, who have pedagogy experience. The survey contained 12 questions and a pilot study was first conducted. The survey was then sent to all teachers in multiple departments across different campuses of the university of interest in Sweden: Lule{\aa} University of Technology. The survey was available in both Swedish and English. The results show that 35 teachers (more than half) use GenAI out of 67 respondents. Preparation is the teaching activity with the most frequency that GenAI is used for and ChatGPT is the most commonly used GenAI. 59% say it has impacted their teaching, however, 55% say there should be legislation around the use of GenAI, especially as inaccuracies and cheating are the biggest concerns.
Authors: Jifan Yu, Xiaohan Zhang, Yifan Xu, Xuanyu Lei, Zijun Yao, Jing Zhang, Lei Hou, Juanzi Li
Abstract: Empowered by the large-scale pretrained language models, existing dialogue systems have demonstrated impressive performance conducting fluent and natural-sounding conversations. However, they are still plagued by the hallucination problem, causing unpredictable factual errors in the generated responses. Recently, knowledge-grounded dialogue generation models, that intentionally invoke external knowledge resources to more informative responses, are also proven to be effective in reducing hallucination. Following the idea of getting high-quality knowledge, a few efforts have achieved pretty good performance on this issue. As some inevitable knowledge noises may also lead to hallucinations, it is emergent to investigate the reason and future directions for building noise-tolerant methods in KGD tasks. In this paper, we analyze the causal story behind this problem with counterfactual reasoning methods. Based on the causal effect analysis, we propose a possible solution for alleviating the hallucination in KGD by exploiting the dialogue-knowledge interaction. Experimental results of our example implementation show that this method can reduce hallucination without disrupting other dialogue performance, while keeping adaptive to different generation models. We hope our efforts can support and call for more attention to developing lightweight techniques towards robust and trusty dialogue systems.
Authors: Chengkai Huang, Rui Wang, Kaige Xie, Tong Yu, Lina Yao
Abstract: Retrieval-augmented large language models (LLMs) have been remarkably competent in various NLP tasks. Despite their great success, the knowledge provided by the retrieval process is not always useful for improving the model prediction, since in some samples LLMs may already be quite knowledgeable and thus be able to answer the question correctly without retrieval. Aiming to save the cost of retrieval, previous work has proposed to determine when to do/skip the retrieval in a data-aware manner by analyzing the LLMs' pretraining data. However, these data-aware methods pose privacy risks and memory limitations, especially when requiring access to sensitive or extensive pretraining data. Moreover, these methods offer limited adaptability under fine-tuning or continual learning settings. We hypothesize that token embeddings are able to capture the model's intrinsic knowledge, which offers a safer and more straightforward way to judge the need for retrieval without the privacy risks associated with accessing pre-training data. Moreover, it alleviates the need to retain all the data utilized during model pre-training, necessitating only the upkeep of the token embeddings. Extensive experiments and in-depth analyses demonstrate the superiority of our model-aware approach.
Authors: Azmine Toushik Wasi, Taki Hasan Rafi, Raima Islam, Dong-Kyu Chae
Abstract: Knowledge Graphs (KGs) have proven essential in information processing and reasoning applications because they link related entities and give context-rich information, supporting efficient information retrieval and knowledge discovery; presenting information flow in a very effective manner. Despite being widely used globally, Bangla is relatively underrepresented in KGs due to a lack of comprehensive datasets, encoders, NER (named entity recognition) models, POS (part-of-speech) taggers, and lemmatizers, hindering efficient information processing and reasoning applications in the language. Addressing the KG scarcity in Bengali, we propose BanglaAutoKG, a pioneering framework that is able to automatically construct Bengali KGs from any Bangla text. We utilize multilingual LLMs to understand various languages and correlate entities and relations universally. By employing a translation dictionary to identify English equivalents and extracting word features from pre-trained BERT models, we construct the foundational KG. To reduce noise and align word embeddings with our goal, we employ graph-based polynomial filters. Lastly, we implement a GNN-based semantic filter, which elevates contextual understanding and trims unnecessary edges, culminating in the formation of the definitive KG. Empirical findings and case studies demonstrate the universal effectiveness of our model, capable of autonomously constructing semantically enriched KGs from any text.
Authors: Yuchen Fan, Yantao Liu, Zijun Yao, Jifan Yu, Lei Hou, Juanzi Li
Abstract: Modern Large Language Models (LLMs) have showcased remarkable prowess in various tasks necessitating sophisticated cognitive behaviors. Nevertheless, a paradoxical performance discrepancy is observed, where these models underperform in seemingly elementary tasks like relation extraction and event extraction due to two issues in conventional evaluation. (1) The imprecision of existing evaluation metrics that struggle to effectively gauge semantic consistency between model outputs and ground truth, and (2) The inherent incompleteness of evaluation benchmarks, primarily due to restrictive human annotation schemas, resulting in underestimated LLM performances. Inspired by the principles in subjective question correction, we propose a new evaluation method, SQC-Score. This method innovatively utilizes LLMs, fine-tuned through subjective question correction data, to refine matching between model outputs and golden labels. Additionally, by incorporating a Natural Language Inference (NLI) model, SQC-Score enriches golden labels, addressing benchmark incompleteness by acknowledging correct yet previously omitted answers. Results on three information extraction tasks show that SQC-Score is more preferred by human annotators than the baseline metrics. Utilizing SQC-Score, we conduct a comprehensive evaluation of the state-of-the-art LLMs and provide insights for future research for information extraction. Dataset and associated codes can be accessed at https://github.com/THU-KEG/SQC-Score.
Authors: Botond Barta, Dorina Lakatos, Attila Nagy, Mil\'an Konor Nyist, Judit \'Acs
Abstract: Training summarization models requires substantial amounts of training data. However for less resourceful languages like Hungarian, openly available models and datasets are notably scarce. To address this gap our paper introduces HunSum-2 an open-source Hungarian corpus suitable for training abstractive and extractive summarization models. The dataset is assembled from segments of the Common Crawl corpus undergoing thorough cleaning, preprocessing and deduplication. In addition to abstractive summarization we generate sentence-level labels for extractive summarization using sentence similarity. We train baseline models for both extractive and abstractive summarization using the collected dataset. To demonstrate the effectiveness of the trained models, we perform both quantitative and qualitative evaluation. Our dataset, models and code are publicly available, encouraging replication, further research, and real-world applications across various domains.
Authors: Harmon Bhasin, Timothy Ossowski, Yiqiao Zhong, Junjie Hu
Abstract: Large language models (LLM) have recently shown the extraordinary ability to perform unseen tasks based on few-shot examples provided as text, also known as in-context learning (ICL). While recent works have attempted to understand the mechanisms driving ICL, few have explored training strategies that incentivize these models to generalize to multiple tasks. Multi-task learning (MTL) for generalist models is a promising direction that offers transfer learning potential, enabling large parameterized models to be trained from simpler, related tasks. In this work, we investigate the combination of MTL with ICL to build models that efficiently learn tasks while being robust to out-of-distribution examples. We propose several effective curriculum learning strategies that allow ICL models to achieve higher data efficiency and more stable convergence. Our experiments reveal that ICL models can effectively learn difficult tasks by training on progressively harder tasks while mixing in prior tasks, denoted as mixed curriculum in this work. Our code and models are available at https://github.com/harmonbhasin/curriculum_learning_icl .
URLs: https://github.com/harmonbhasin/curriculum_learning_icl
Authors: Rohit Saxena, Frank Keller
Abstract: Abstractive summarization for long-form narrative texts such as movie scripts is challenging due to the computational and memory constraints of current language models. A movie script typically comprises a large number of scenes; however, only a fraction of these scenes are salient, i.e., important for understanding the overall narrative. The salience of a scene can be operationalized by considering it as salient if it is mentioned in the summary. Automatically identifying salient scenes is difficult due to the lack of suitable datasets. In this work, we introduce a scene saliency dataset that consists of human-annotated salient scenes for 100 movies. We propose a two-stage abstractive summarization approach which first identifies the salient scenes in script and then generates a summary using only those scenes. Using QA-based evaluation, we show that our model outperforms previous state-of-the-art summarization methods and reflects the information content of a movie more accurately than a model that takes the whole movie script as input.
Authors: Regina Stodden
Abstract: In this work, we propose EASSE-multi, a framework for easier automatic sentence evaluation for languages other than English. Compared to the original EASSE framework, EASSE-multi does not focus only on English. It contains tokenizers and versions of text simplification evaluation metrics which are suitable for multiple languages. In this paper, we exemplify the usage of EASSE-multi for German TS, resulting in EASSE-DE. Further, we compare text simplification results when evaluating with different language or tokenization settings of the metrics. Based on this, we formulate recommendations on how to make the evaluation of (German) TS models more transparent and better comparable. The code of EASSE-multi and its German specialisation (EASSE-DE) can be found at https://github.com/rstodden/easse-de.
Authors: Kai Zhang, Lizhi Qing, Yangyang Kang, Xiaozhong Liu
Abstract: Large Language Models (LLMs) have exhibited remarkable proficiency in comprehending and generating natural language. On the other hand, personalized LLM response generation holds the potential to offer substantial benefits for individuals in critical areas such as medical. Existing research has explored memory-augmented methods to prompt the LLM with pre-stored user-specific knowledge for personalized response generation in terms of new queries. We contend that such paradigm is unable to perceive fine-granularity information. In this study, we propose a novel \textbf{M}emory-\textbf{i}njected approach using parameter-efficient fine-tuning (PEFT) and along with a Bayesian Optimisation searching strategy to achieve \textbf{L}LM \textbf{P}ersonalization(\textbf{MiLP}).
Authors: Yantao Liu, Zijun Yao, Xin Lv, Yuchen Fan, Shulin Cao, Jifan Yu, Lei Hou, Juanzi Li
Abstract: Providing knowledge documents for large language models (LLMs) has emerged as a promising solution to update the static knowledge inherent in their parameters. However, knowledge in the document may conflict with the memory of LLMs due to outdated or incorrect knowledge in the LLMs' parameters. This leads to the necessity of examining the capability of LLMs to assimilate supplemental external knowledge that conflicts with their memory. While previous studies have explained to what extent LLMs extract conflicting knowledge from the provided text, they neglect the necessity to reason with conflicting knowledge. Furthermore, there lack a detailed analysis on strategies to enable LLMs to resolve conflicting knowledge via prompting, decoding strategy, and supervised fine-tuning. To address these limitations, we construct a new dataset, dubbed KNOT, for knowledge conflict resolution examination in the form of question answering. KNOT facilitates in-depth analysis by dividing reasoning with conflicting knowledge into three levels: (1) Direct Extraction, which directly extracts conflicting knowledge to answer questions. (2) Explicit Reasoning, which reasons with conflicting knowledge when the reasoning path is explicitly provided in the question. (3) Implicit Reasoning, where reasoning with conflicting knowledge requires LLMs to infer the reasoning path independently to answer questions. We also conduct extensive experiments on KNOT to establish empirical guidelines for LLMs to utilize conflicting knowledge in complex circumstances. Dataset and associated codes can be accessed at https://github.com/THU-KEG/KNOT .
Authors: Zhengxuan Wu, Aryaman Arora, Zheng Wang, Atticus Geiger, Dan Jurafsky, Christopher D. Manning, Christopher Potts
Abstract: Parameter-efficient fine-tuning (PEFT) methods seek to adapt large models via updates to a small number of weights. However, much prior interpretability work has shown that representations encode rich semantic information, suggesting that editing representations might be a more powerful alternative. Here, we pursue this hypothesis by developing a family of $\textbf{Representation Finetuning (ReFT)}$ methods. ReFT methods operate on a frozen base model and learn task-specific interventions on hidden representations. We define a strong instance of the ReFT family, Low-rank Linear Subspace ReFT (LoReFT). LoReFT is a drop-in replacement for existing PEFTs and learns interventions that are 10x-50x more parameter-efficient than prior state-of-the-art PEFTs. We showcase LoReFT on eight commonsense reasoning tasks, four arithmetic reasoning tasks, Alpaca-Eval v1.0, and GLUE. In all these evaluations, LoReFT delivers the best balance of efficiency and performance, and almost always outperforms state-of-the-art PEFTs. We release a generic ReFT training library publicly at https://github.com/stanfordnlp/pyreft.
Authors: Ankan Mullick, Mukur Gupta, Pawan Goyal
Abstract: Biomedical queries have become increasingly prevalent in web searches, reflecting the growing interest in accessing biomedical literature. Despite recent research on large-language models (LLMs) motivated by endeavours to attain generalized intelligence, their efficacy in replacing task and domain-specific natural language understanding approaches remains questionable. In this paper, we address this question by conducting a comprehensive empirical evaluation of intent detection and named entity recognition (NER) tasks from biomedical text. We show that Supervised Fine Tuned approaches are still relevant and more effective than general-purpose LLMs. Biomedical transformer models such as PubMedBERT can surpass ChatGPT on NER task with only 5 supervised examples.
Authors: Ryo Kamoi, Sarkar Snigdha Sarathi Das, Renze Lou, Jihyun Janice Ahn, Yilun Zhao, Xiaoxin Lu, Nan Zhang, Yusen Zhang, Ranran Haoran Zhang, Sujeeth Reddy Vummanthala, Salika Dave, Shaobo Qin, Arman Cohan, Wenpeng Yin, Rui Zhang
Abstract: With Large Language Models (LLMs) being widely used across various tasks, detecting errors in their responses is increasingly crucial. However, little research has been conducted on error detection of LLM responses. Collecting error annotations on LLM responses is challenging due to the subjective nature of many NLP tasks, and thus previous research focuses on tasks of little practical value (e.g., word sorting) or limited error types (e.g., faithfulness in summarization). This work introduces ReaLMistake, the first error detection benchmark consisting of objective, realistic, and diverse errors made by LLMs. ReaLMistake contains three challenging and meaningful tasks that introduce objectively assessable errors in four categories (reasoning correctness, instruction-following, context-faithfulness, and parameterized knowledge), eliciting naturally observed and diverse errors in responses of GPT-4 and Llama 2 70B annotated by experts. We use ReaLMistake to evaluate error detectors based on 12 LLMs. Our findings show: 1) Top LLMs like GPT-4 and Claude 3 detect errors made by LLMs at very low recall, and all LLM-based error detectors perform much worse than humans. 2) Explanations by LLM-based error detectors lack reliability. 3) LLMs-based error detection is sensitive to small changes in prompts but remains challenging to improve. 4) Popular approaches to improving LLMs, including self-consistency and majority vote, do not improve the error detection performance. Our benchmark and code are provided at https://github.com/psunlpgroup/ReaLMistake.
Authors: Longxu Dou, Qian Liu, Guangtao Zeng, Jia Guo, Jiahui Zhou, Wei Lu, Min Lin
Abstract: We present Sailor, a family of open language models ranging from 0.5B to 7B parameters, tailored for South-East Asian (SEA) languages. These models are continually pre-trained from Qwen1.5, a great language model for multilingual use cases. From Qwen1.5, Sailor models accept 200B to 400B tokens, primarily covering the languages of English, Chinese, Vietnamese, Thai, Indonesian, Malay, and Lao. The training leverages several techniques, including BPE dropout for improving the model robustness, aggressive data cleaning and deduplication, and small proxy models to optimize data mixture. Experimental results on four typical tasks indicate that Sailor models demonstrate strong performance across different benchmarks, including commonsense reasoning, question answering, reading comprehension and examination. Embracing the open-source spirit, we share our insights through this report to spark a wider interest in developing large language models for multilingual use cases.
Authors: Wenshan Wu, Shaoguang Mao, Yadong Zhang, Yan Xia, Li Dong, Lei Cui, Furu Wei
Abstract: Large language models (LLMs) have exhibited impressive performance in language comprehension and various reasoning tasks. However, their abilities in spatial reasoning, a crucial aspect of human cognition, remain relatively unexplored. Human possess a remarkable ability to create mental images of unseen objects and actions through a process known as \textbf{the Mind's Eye}, enabling the imagination of the unseen world. Inspired by this cognitive capacity, we propose Visualization-of-Thought (\textbf{VoT}) prompting. VoT aims to elicit spatial reasoning of LLMs by visualizing their reasoning traces, thereby guiding subsequent reasoning steps. We employed VoT for multi-hop spatial reasoning tasks, including natural language navigation, visual navigation, and visual tiling in 2D grid worlds. Experimental results demonstrated that VoT significantly enhances the spatial reasoning abilities of LLMs. Notably, VoT outperformed existing multimodal large language models (MLLMs) in these tasks. While VoT works surprisingly well on LLMs, the ability to generate \textit{mental images} to facilitate spatial reasoning resembles the mind's eye process, suggesting its potential viability in MLLMs.
Authors: Marco Bronzini, Carlo Nicolini, Bruno Lepri, Jacopo Staiano, Andrea Passerini
Abstract: Large Language Models (LLMs) demonstrate an impressive capacity to recall a vast range of common factual knowledge information. However, unravelling the underlying reasoning of LLMs and explaining their internal mechanisms of exploiting this factual knowledge remain active areas of investigation. Our work analyzes the factual knowledge encoded in the latent representation of LLMs when prompted to assess the truthfulness of factual claims. We propose an end-to-end framework that jointly decodes the factual knowledge embedded in the latent space of LLMs from a vector space to a set of ground predicates and represents its evolution across the layers using a temporal knowledge graph. Our framework relies on the technique of activation patching which intervenes in the inference computation of a model by dynamically altering its latent representations. Consequently, we neither rely on external models nor training processes. We showcase our framework with local and global interpretability analyses using two claim verification datasets: FEVER and CLIMATE-FEVER. The local interpretability analysis exposes different latent errors from representation to multi-hop reasoning errors. On the other hand, the global analysis uncovered patterns in the underlying evolution of the model's factual knowledge (e.g., store-and-seek factual information). By enabling graph-based analyses of the latent representations, this work represents a step towards the mechanistic interpretability of LLMs.
Authors: Brian Lester, Jaehoon Lee, Alex Alemi, Jeffrey Pennington, Adam Roberts, Jascha Sohl-Dickstein, Noah Constant
Abstract: In this paper, we explore the idea of training large language models (LLMs) over highly compressed text. While standard subword tokenizers compress text by a small factor, neural text compressors can achieve much higher rates of compression. If it were possible to train LLMs directly over neurally compressed text, this would confer advantages in training and serving efficiency, as well as easier handling of long text spans. The main obstacle to this goal is that strong compression tends to produce opaque outputs that are not well-suited for learning. In particular, we find that text na\"ively compressed via Arithmetic Coding is not readily learnable by LLMs. To overcome this, we propose Equal-Info Windows, a novel compression technique whereby text is segmented into blocks that each compress to the same bit length. Using this method, we demonstrate effective learning over neurally compressed text that improves with scale, and outperforms byte-level baselines by a wide margin on perplexity and inference speed benchmarks. While our method delivers worse perplexity than subword tokenizers for models trained with the same parameter count, it has the benefit of shorter sequence lengths. Shorter sequence lengths require fewer autoregressive generation steps, and reduce latency. Finally, we provide extensive analysis of the properties that contribute to learnability, and offer concrete suggestions for how to further improve the performance of high-compression tokenizers.
Authors: Arnab Sen Sharma, David Atkinson, David Bau
Abstract: We investigate the mechanisms of factual recall in the Mamba state space model. Our work is inspired by previous findings in autoregressive transformer language models suggesting that their knowledge recall is localized to particular modules at specific token locations; we therefore ask whether factual recall in Mamba can be similarly localized. To investigate this, we conduct four lines of experiments on Mamba. First, we apply causal tracing or interchange interventions to localize key components inside Mamba that are responsible for recalling facts, revealing that specific components within middle layers show strong causal effects at the last token of the subject, while the causal effect of intervening on later layers is most pronounced at the last token of the prompt, matching previous findings on autoregressive transformers. Second, we show that rank-one model editing methods can successfully insert facts at specific locations, again resembling findings on transformer models. Third, we examine the linearity of Mamba's representations of factual relations. Finally we adapt attention-knockout techniques to Mamba to dissect information flow during factual recall. We compare Mamba directly to a similar-sized transformer and conclude that despite significant differences in architectural approach, when it comes to factual recall, the two architectures share many similarities.
Authors: Hanyu Lai, Xiao Liu, Iat Long Iong, Shuntian Yao, Yuxuan Chen, Pengbo Shen, Hao Yu, Hanchen Zhang, Xiaohan Zhang, Yuxiao Dong, Jie Tang
Abstract: Large language models (LLMs) have fueled many intelligent agent tasks, such as web navigation -- but most existing agents perform far from satisfying in real-world webpages due to three factors: (1) the versatility of actions on webpages, (2) HTML text exceeding model processing capacity, and (3) the complexity of decision-making due to the open-domain nature of web. In light of the challenge, we develop AutoWebGLM, a GPT-4-outperforming automated web navigation agent built upon ChatGLM3-6B. Inspired by human browsing patterns, we design an HTML simplification algorithm to represent webpages, preserving vital information succinctly. We employ a hybrid human-AI method to build web browsing data for curriculum training. Then, we bootstrap the model by reinforcement learning and rejection sampling to further facilitate webpage comprehension, browser operations, and efficient task decomposition by itself. For testing, we establish a bilingual benchmark -- AutoWebBench -- for real-world web browsing tasks. We evaluate AutoWebGLM across diverse web navigation benchmarks, revealing its improvements but also underlying challenges to tackle real environments. Related code, model, and data will be released at \url{https://github.com/THUDM/AutoWebGLM}.
Authors: Amir H. Abdi, Xinye Tang, Jeremias Eichelbaum, Mahan Das, Alex Klein, Nihal Irmak Pakis, William Blum, Daniel L Mace, Tanvi Raja, Namrata Padmanabhan, Ye Xing
Abstract: Data is growing rapidly in volume and complexity. Proficiency in database query languages is pivotal for crafting effective queries. As coding assistants become more prevalent, there is significant opportunity to enhance database query languages. The Kusto Query Language (KQL) is a widely used query language for large semi-structured data such as logs, telemetries, and time-series for big data analytics platforms. This paper introduces NL2KQL an innovative framework that uses large language models (LLMs) to convert natural language queries (NLQs) to KQL queries. The proposed NL2KQL framework includes several key components: Schema Refiner which narrows down the schema to its most pertinent elements; the Few-shot Selector which dynamically selects relevant examples from a few-shot dataset; and the Query Refiner which repairs syntactic and semantic errors in KQL queries. Additionally, this study outlines a method for generating large datasets of synthetic NLQ-KQL pairs which are valid within a specific database contexts. To validate NL2KQL's performance, we utilize an array of online (based on query execution) and offline (based on query parsing) metrics. Through ablation studies, the significance of each framework component is examined, and the datasets used for benchmarking are made publicly available. This work is the first of its kind and is compared with available baselines to demonstrate its effectiveness.
Authors: Weidi Luo, Siyuan Ma, Xiaogeng Liu, Xiaoyu Guo, Chaowei Xiao
Abstract: With the rapid advancements in Multimodal Large Language Models (MLLMs), securing these models against malicious inputs while aligning them with human values has emerged as a critical challenge. In this paper, we investigate an important and unexplored question of whether techniques that successfully jailbreak Large Language Models (LLMs) can be equally effective in jailbreaking MLLMs. To explore this issue, we introduce JailBreakV-28K, a pioneering benchmark designed to assess the transferability of LLM jailbreak techniques to MLLMs, thereby evaluating the robustness of MLLMs against diverse jailbreak attacks. Utilizing a dataset of 2, 000 malicious queries that is also proposed in this paper, we generate 20, 000 text-based jailbreak prompts using advanced jailbreak attacks on LLMs, alongside 8, 000 image-based jailbreak inputs from recent MLLMs jailbreak attacks, our comprehensive dataset includes 28, 000 test cases across a spectrum of adversarial scenarios. Our evaluation of 10 open-source MLLMs reveals a notably high Attack Success Rate (ASR) for attacks transferred from LLMs, highlighting a critical vulnerability in MLLMs that stems from their text-processing capabilities. Our findings underscore the urgent need for future research to address alignment vulnerabilities in MLLMs from both textual and visual inputs.
Authors: Vibhor Agarwal, Aravindh Raman, Nishanth Sastry, Ahmed M. Abdelmoniem, Gareth Tyson, Ignacio Castro
Abstract: The recent development of decentralised and interoperable social networks (such as the "fediverse") creates new challenges for content moderators. This is because millions of posts generated on one server can easily "spread" to another, even if the recipient server has very different moderation policies. An obvious solution would be to leverage moderation tools to automatically tag (and filter) posts that contravene moderation policies, e.g. related to toxic speech. Recent work has exploited the conversational context of a post to improve this automatic tagging, e.g. using the replies to a post to help classify if it contains toxic speech. This has shown particular potential in environments with large training sets that contain complete conversations. This, however, creates challenges in a decentralised context, as a single conversation may be fragmented across multiple servers. Thus, each server only has a partial view of an entire conversation because conversations are often federated across servers in a non-synchronized fashion. To address this, we propose a decentralised conversation-aware content moderation approach suitable for the fediverse. Our approach employs a graph deep learning model (GraphNLI) trained locally on each server. The model exploits local data to train a model that combines post and conversational information captured through random walks to detect toxicity. We evaluate our approach with data from Pleroma, a major decentralised and interoperable micro-blogging network containing 2 million conversations. Our model effectively detects toxicity on larger instances, exclusively trained using their local post information (0.8837 macro-F1). Our approach has considerable scope to improve moderation in decentralised and interoperable social networks such as Pleroma or Mastodon.
Authors: Johann D. Gaebler, Sharad Goel, Aziz Huq, Prasanna Tambe
Abstract: Regulatory efforts to protect against algorithmic bias have taken on increased urgency with rapid advances in large language models (LLMs), which are machine learning models that can achieve performance rivaling human experts on a wide array of tasks. A key theme of these initiatives is algorithmic "auditing," but current regulations -- as well as the scientific literature -- provide little guidance on how to conduct these assessments. Here we propose and investigate one approach for auditing algorithms: correspondence experiments, a widely applied tool for detecting bias in human judgements. In the employment context, correspondence experiments aim to measure the extent to which race and gender impact decisions by experimentally manipulating elements of submitted application materials that suggest an applicant's demographic traits, such as their listed name. We apply this method to audit candidate assessments produced by several state-of-the-art LLMs, using a novel corpus of applications to K-12 teaching positions in a large public school district. We find evidence of moderate race and gender disparities, a pattern largely robust to varying the types of application material input to the models, as well as the framing of the task to the LLMs. We conclude by discussing some important limitations of correspondence experiments for auditing algorithms.
Authors: William Macke, Michael Doyle
Abstract: Large Language Models (LLMs) have demonstrated impressive abilities in recent years with regards to code generation and understanding. However, little work has investigated how documentation and other code properties affect an LLM's ability to understand and generate code or documentation. We present an empirical analysis of how underlying properties of code or documentation can affect an LLM's capabilities. We show that providing an LLM with "incorrect" documentation can greatly hinder code understanding, while incomplete or missing documentation does not seem to significantly affect an LLM's ability to understand code.
Authors: Taichi Nishimura, Koki Yamamoto, Yuto Haneji, Keiya Kajimura, Chihiro Nishiwaki, Eriko Daikoku, Natsuko Okuda, Fumihito Ono, Hirotaka Kameko, Shinsuke Mori
Abstract: This paper introduces a biochemical vision-and-language dataset, which consists of 24 egocentric experiment videos, corresponding protocols, and video-and-language alignments. The key challenge in the wet-lab domain is detecting equipment, reagents, and containers is difficult because the lab environment is scattered by filling objects on the table and some objects are indistinguishable. Therefore, previous studies assume that objects are manually annotated and given for downstream tasks, but this is costly and time-consuming. To address this issue, this study focuses on Micro QR Codes to detect objects automatically. From our preliminary study, we found that detecting objects only using Micro QR Codes is still difficult because the researchers manipulate objects, causing blur and occlusion frequently. To address this, we also propose a novel object labeling method by combining a Micro QR Code detector and an off-the-shelf hand object detector. As one of the applications of our dataset, we conduct the task of generating protocols from experiment videos and find that our approach can generate accurate protocols.
Authors: Yuan Wang, Xuyang Wu, Hsin-Tai Wu, Zhiqiang Tao, Yi Fang
Abstract: The integration of Large Language Models (LLMs) in information retrieval has raised a critical reevaluation of fairness in the text-ranking models. LLMs, such as GPT models and Llama2, have shown effectiveness in natural language understanding tasks, and prior works (e.g., RankGPT) have also demonstrated that the LLMs exhibit better performance than the traditional ranking models in the ranking task. However, their fairness remains largely unexplored. This paper presents an empirical study evaluating these LLMs using the TREC Fair Ranking dataset, focusing on the representation of binary protected attributes such as gender and geographic location, which are historically underrepresented in search outcomes. Our analysis delves into how these LLMs handle queries and documents related to these attributes, aiming to uncover biases in their ranking algorithms. We assess fairness from both user and content perspectives, contributing an empirical benchmark for evaluating LLMs as the fair ranker.
Authors: Detai Xin, Xu Tan, Kai Shen, Zeqian Ju, Dongchao Yang, Yuancheng Wang, Shinnosuke Takamichi, Hiroshi Saruwatari, Shujie Liu, Jinyu Li, Sheng Zhao
Abstract: We present RALL-E, a robust language modeling method for text-to-speech (TTS) synthesis. While previous work based on large language models (LLMs) shows impressive performance on zero-shot TTS, such methods often suffer from poor robustness, such as unstable prosody (weird pitch and rhythm/duration) and a high word error rate (WER), due to the autoregressive prediction style of language models. The core idea behind RALL-E is chain-of-thought (CoT) prompting, which decomposes the task into simpler steps to enhance the robustness of LLM-based TTS. To accomplish this idea, RALL-E first predicts prosody features (pitch and duration) of the input text and uses them as intermediate conditions to predict speech tokens in a CoT style. Second, RALL-E utilizes the predicted duration prompt to guide the computing of self-attention weights in Transformer to enforce the model to focus on the corresponding phonemes and prosody features when predicting speech tokens. Results of comprehensive objective and subjective evaluations demonstrate that, compared to a powerful baseline method VALL-E, RALL-E significantly improves the WER of zero-shot TTS from $6.3\%$ (without reranking) and $2.1\%$ (with reranking) to $2.8\%$ and $1.0\%$, respectively. Furthermore, we demonstrate that RALL-E correctly synthesizes sentences that are hard for VALL-E and reduces the error rate from $68\%$ to $4\%$.
Authors: Shuo Chen, Zhen Han, Bailan He, Zifeng Ding, Wenqian Yu, Philip Torr, Volker Tresp, Jindong Gu
Abstract: Various jailbreak attacks have been proposed to red-team Large Language Models (LLMs) and revealed the vulnerable safeguards of LLMs. Besides, some methods are not limited to the textual modality and extend the jailbreak attack to Multimodal Large Language Models (MLLMs) by perturbing the visual input. However, the absence of a universal evaluation benchmark complicates the performance reproduction and fair comparison. Besides, there is a lack of comprehensive evaluation of closed-source state-of-the-art (SOTA) models, especially MLLMs, such as GPT-4V. To address these issues, this work first builds a comprehensive jailbreak evaluation dataset with 1445 harmful questions covering 11 different safety policies. Based on this dataset, extensive red-teaming experiments are conducted on 11 different LLMs and MLLMs, including both SOTA proprietary models and open-source models. We then conduct a deep analysis of the evaluated results and find that (1) GPT4 and GPT-4V demonstrate better robustness against jailbreak attacks compared to open-source LLMs and MLLMs. (2) Llama2 and Qwen-VL-Chat are more robust compared to other open-source models. (3) The transferability of visual jailbreak methods is relatively limited compared to textual jailbreak methods. The dataset and code can be found here https://anonymous.4open.science/r/red_teaming_gpt4-C1CE/README.md .
URLs: https://anonymous.4open.science/r/red_teaming_gpt4-C1CE/README.md
Authors: Sean McLeish, Avi Schwarzschild, Tom Goldstein
Abstract: We evaluate ChatGPT's ability to solve algorithm problems from the CLRS benchmark suite that is designed for GNNs. The benchmark requires the use of a specified classical algorithm to solve a given problem. We find that ChatGPT outperforms specialist GNN models, using Python to successfully solve these problems. This raises new points in the discussion about learning algorithms with neural networks.
Authors: Jiawei Guo, Ziming Li, Xueling Liu, Kaijing Ma, Tianyu Zheng, Zhouliang Yu, Ding Pan, Yizhi LI, Ruibo Liu, Yue Wang, Shuyue Guo, Xingwei Qu, Xiang Yue, Ge Zhang, Wenhu Chen, Jie Fu
Abstract: Large Language Models (LLMs) for code are rapidly evolving, with code editing emerging as a critical capability. We introduce CodeEditorBench, an evaluation framework designed to rigorously assess the performance of LLMs in code editing tasks, including debugging, translating, polishing, and requirement switching. Unlike existing benchmarks focusing solely on code generation, CodeEditorBench emphasizes real-world scenarios and practical aspects of software development. We curate diverse coding challenges and scenarios from five sources, covering various programming languages, complexity levels, and editing tasks. Evaluation of 19 LLMs reveals that closed-source models (particularly Gemini-Ultra and GPT-4), outperform open-source models in CodeEditorBench, highlighting differences in model performance based on problem types and prompt sensitivities. CodeEditorBench aims to catalyze advancements in LLMs by providing a robust platform for assessing code editing capabilities. We will release all prompts and datasets to enable the community to expand the dataset and benchmark emerging LLMs. By introducing CodeEditorBench, we contribute to the advancement of LLMs in code editing and provide a valuable resource for researchers and practitioners.
Authors: Aniruddha Nrusimha, Mayank Mishra, Naigang Wang, Dan Alistarh, Rameswar Panda, Yoon Kim
Abstract: We consider the problem of accurate quantization for language models, where both the weights and activations are uniformly quantized to 4 bits per parameter, the lowest bitwidth format natively supported by GPU hardware. In this context, the key challenge is activation quantization: it is known that language models contain outlier channels whose values on average are orders of magnitude higher than than other channels, which prevents accurate low-bitwidth quantization with known techniques. We systematically study this phenomena and find that these outlier channels emerge early in training, and that they occur more frequently in layers with residual streams. We then propose a simple strategy which regularizes a layer's inputs via quantization-aware training (QAT) and its outputs via activation kurtosis regularization. We show that regularizing both the inputs and outputs is crucial for preventing a model's "migrating" the difficulty in input quantization to the weights, which makes post-training quantization (PTQ) of weights more difficult. When combined with weight PTQ, we show that our approach can obtain a W4A4 model that performs competitively to the standard-precision W16A16 baseline.
Authors: Ziyao Zeng, Daniel Wang, Fengyu Yang, Hyoungseob Park, Yangchao Wu, Stefano Soatto, Byung-Woo Hong, Dong Lao, Alex Wong
Abstract: Three-dimensional (3D) reconstruction from a single image is an ill-posed problem with inherent ambiguities, i.e. scale. Predicting a 3D scene from text description(s) is similarly ill-posed, i.e. spatial arrangements of objects described. We investigate the question of whether two inherently ambiguous modalities can be used in conjunction to produce metric-scaled reconstructions. To test this, we focus on monocular depth estimation, the problem of predicting a dense depth map from a single image, but with an additional text caption describing the scene. To this end, we begin by encoding the text caption as a mean and standard deviation; using a variational framework, we learn the distribution of the plausible metric reconstructions of 3D scenes corresponding to the text captions as a prior. To "select" a specific reconstruction or depth map, we encode the given image through a conditional sampler that samples from the latent space of the variational text encoder, which is then decoded to the output depth map. Our approach is trained alternatingly between the text and image branches: in one optimization step, we predict the mean and standard deviation from the text description and sample from a standard Gaussian, and in the other, we sample using a (image) conditional sampler. Once trained, we directly predict depth from the encoded text using the conditional sampler. We demonstrate our approach on indoor (NYUv2) and outdoor (KITTI) scenarios, where we show that language can consistently improve performance in both.
Authors: Dongzhi Jiang, Guanglu Song, Xiaoshi Wu, Renrui Zhang, Dazhong Shen, Zhuofan Zong, Yu Liu, Hongsheng Li
Abstract: Diffusion models have demonstrated great success in the field of text-to-image generation. However, alleviating the misalignment between the text prompts and images is still challenging. The root reason behind the misalignment has not been extensively investigated. We observe that the misalignment is caused by inadequate token attention activation. We further attribute this phenomenon to the diffusion model's insufficient condition utilization, which is caused by its training paradigm. To address the issue, we propose CoMat, an end-to-end diffusion model fine-tuning strategy with an image-to-text concept matching mechanism. We leverage an image captioning model to measure image-to-text alignment and guide the diffusion model to revisit ignored tokens. A novel attribute concentration module is also proposed to address the attribute binding problem. Without any image or human preference data, we use only 20K text prompts to fine-tune SDXL to obtain CoMat-SDXL. Extensive experiments show that CoMat-SDXL significantly outperforms the baseline model SDXL in two text-to-image alignment benchmarks and achieves start-of-the-art performance.
Authors: Hongfei Xu, Yang Song, Qiuhui Liu, Josef van Genabith, Deyi Xiong
Abstract: Stacking non-linear layers allows deep neural networks to model complicated functions, and including residual connections in Transformer layers is beneficial for convergence and performance. However, residual connections may make the model "forget" distant layers and fail to fuse information from previous layers effectively. Selectively managing the representation aggregation of Transformer layers may lead to better performance. In this paper, we present a Transformer with depth-wise LSTMs connecting cascading Transformer layers and sub-layers. We show that layer normalization and feed-forward computation within a Transformer layer can be absorbed into depth-wise LSTMs connecting pure Transformer attention layers. Our experiments with the 6-layer Transformer show significant BLEU improvements in both WMT 14 English-German / French tasks and the OPUS-100 many-to-many multilingual NMT task, and our deep Transformer experiments demonstrate the effectiveness of depth-wise LSTM on the convergence and performance of deep Transformers.
Authors: Chen Cecilia Liu, Jonas Pfeiffer, Ivan Vuli\'c, Iryna Gurevych
Abstract: Standard fine-tuning of language models typically performs well on in-distribution data, but suffers with generalization to distribution shifts. In this work, we aim to improve the generalization of adapter-based cross-lingual task transfer where such cross-language distribution shifts are imminent. We investigate scheduled unfreezing algorithms -- originally proposed to mitigate catastrophic forgetting in transfer learning -- for fine-tuning task adapters. Our experiments show that scheduled unfreezing methods close the gap to full fine-tuning and achieve stronger cross-lingual transfer performance, suggesting that these methods can go beyond just mitigating catastrophic forgetting. Next, aiming to understand these empirical findings, we investigate the learning dynamics of scheduled unfreezing using Fisher Information. Our experiments reveal that scheduled unfreezing induces different learning dynamics compared to standard fine-tuning, and provide evidence that the dynamics of Fisher Information during training correlate with cross-lingual generalization performance. We additionally propose a general scheduled unfreezing algorithm that achieves an average of 2 points improvement over four datasets compared to standard fine-tuning and provides empirical evidence for a theory-based justification of the heuristic unfreezing schedule for adapter training.
Authors: Lukas Galke, Yoav Ram, Limor Raviv
Abstract: Deep neural networks drive the success of natural language processing. A fundamental property of language is its compositional structure, allowing humans to systematically produce forms for new meanings. For humans, languages with more compositional and transparent structures are typically easier to learn than those with opaque and irregular structures. However, this learnability advantage has not yet been shown for deep neural networks, limiting their use as models for human language learning. Here, we directly test how neural networks compare to humans in learning and generalizing different languages that vary in their degree of compositional structure. We evaluate the memorization and generalization capabilities of a large language model and recurrent neural networks, and show that both deep neural networks exhibit a learnability advantage for more structured linguistic input: neural networks exposed to more compositional languages show more systematic generalization, greater agreement between different agents, and greater similarity to human learners.
Authors: Albert Yu Sun, Varun Nair, Elliot Schumacher, Anitha Kannan
Abstract: A wave of new task-based virtual assistants has been fueled by increasingly powerful large language models (LLMs), such as GPT-4 (OpenAI, 2023). A major challenge in deploying LLM-based virtual conversational assistants in real world settings is ensuring they operate within what is admissible for the task. To overcome this challenge, the designers of these virtual assistants rely on an independent guardrail system that verifies the virtual assistant's output aligns with the constraints required for the task. However, relying on commonly used, prompt-based guardrails can be difficult to engineer correctly and comprehensively. To address these challenges, we propose CONSCENDI. We use CONSCENDI to exhaustively generate training data with two key LLM-powered components: scenario-augmented generation and contrastive training examples. When generating conversational data, we generate a set of rule-breaking scenarios, which enumerate a diverse set of high-level ways a rule can be violated. This scenario-guided approach produces a diverse training set and provides chatbot designers greater control. To generate contrastive examples, we prompt the LLM to alter conversations with violations into acceptable conversations to enable fine-grained distinctions. We then use this data, generated by CONSCENDI, to train a smaller model. We find that CONSCENDI results in guardrail models that improve over baselines in multiple dialogue domains.
Authors: William Rudman, Carsten Eickhoff
Abstract: Given the success of Large Language Models (LLMs), there has been considerable interest in studying the properties of model activations. The literature overwhelmingly agrees that LLM representations are dominated by a few "outlier dimensions" with exceedingly high variance and magnitude. Several studies in Natural Language Processing (NLP) have sought to mitigate the impact of such outlier dimensions and force LLMs to be isotropic (i.e., have uniform variance across all dimensions in embedding space). Isotropy is thought to be a desirable property for LLMs that improves model performance and more closely aligns textual representations with human intuition. However, many of the claims regarding isotropy in NLP have been based on the average cosine similarity of embeddings, which has recently been shown to be a flawed measure of isotropy. In this paper, we propose I-STAR: IsoScore*-based STable Anisotropic Regularization, a novel regularization method that can be used to increase or decrease levels of isotropy in embedding space during training. I-STAR uses IsoScore*, the first accurate measure of isotropy that is both differentiable and stable on mini-batch computations. In contrast to several previous works, we find that decreasing isotropy in contextualized embeddings improves performance on the majority of tasks and models considered in this paper.
Authors: Xidong Wang, Guiming Hardy Chen, Dingjie Song, Zhiyi Zhang, Zhihong Chen, Qingying Xiao, Feng Jiang, Jianquan Li, Xiang Wan, Benyou Wang, Haizhou Li
Abstract: Large Language Models (LLMs) provide a possibility to make a great breakthrough in medicine. The establishment of a standardized medical benchmark becomes a fundamental cornerstone to measure progression. However, medical environments in different regions have their local characteristics, e.g., the ubiquity and significance of traditional Chinese medicine within China. Therefore, merely translating English-based medical evaluation may result in \textit{contextual incongruities} to a local region. To solve the issue, we propose a localized medical benchmark called CMB, a Comprehensive Medical Benchmark in Chinese, designed and rooted entirely within the native Chinese linguistic and cultural framework. While traditional Chinese medicine is integral to this evaluation, it does not constitute its entirety. Using this benchmark, we have evaluated several prominent large-scale LLMs, including ChatGPT, GPT-4, dedicated Chinese LLMs, and LLMs specialized in the medical domain. We hope this benchmark provide first-hand experience in existing LLMs for medicine and also facilitate the widespread adoption and enhancement of medical LLMs within China. Our data and code are publicly available at https://github.com/FreedomIntelligence/CMB.
Authors: Kai Zhang, Yangyang Kang, Fubang Zhao, Xiaozhong Liu
Abstract: Large Language Models (LLMs), such as GPT3.5, have exhibited remarkable proficiency in comprehending and generating natural language. On the other hand, medical assistants hold the potential to offer substantial benefits for individuals. However, the exploration of LLM-based personalized medical assistant remains relatively scarce. Typically, patients converse differently based on their background and preferences which necessitates the task of enhancing user-oriented medical assistant. While one can fully train an LLM for this objective, the resource consumption is unaffordable. Prior research has explored memory-based methods to enhance the response with aware of previous mistakes for new queries during a dialogue session. We contend that a mere memory module is inadequate and fully training an LLM can be excessively costly. In this study, we propose a novel computational bionic memory mechanism, equipped with a parameter-efficient fine-tuning (PEFT) schema, to personalize medical assistants.
Authors: Xuansheng Wu, Wenlin Yao, Jianshu Chen, Xiaoman Pan, Xiaoyang Wang, Ninghao Liu, Dong Yu
Abstract: Large Language Models (LLMs) have achieved remarkable success, where instruction tuning is the critical step in aligning LLMs with user intentions. In this work, we investigate how the instruction tuning adjusts pre-trained models with a focus on intrinsic changes. Specifically, we first develop several local and global explanation methods, including a gradient-based method for input-output attribution, and techniques for interpreting patterns and concepts in self-attention and feed-forward layers. The impact of instruction tuning is then studied by comparing the explanations derived from the pre-trained and instruction-tuned models. This approach provides an internal perspective of the model shifts on a human-comprehensible level. Our findings reveal three significant impacts of instruction tuning: 1) It empowers LLMs to recognize the instruction parts of user prompts, and promotes the response generation constantly conditioned on the instructions. 2) It encourages the self-attention heads to capture more word-word relationships about instruction verbs. 3) It encourages the feed-forward networks to rotate their pre-trained knowledge toward user-oriented tasks. These insights contribute to a more comprehensive understanding of instruction tuning and lay the groundwork for future work that aims at explaining and optimizing LLMs for various applications. Our code and data are publicly available at https://github.com/JacksonWuxs/Interpret_Instruction_Tuning_LLMs.
URLs: https://github.com/JacksonWuxs/Interpret_Instruction_Tuning_LLMs.
Authors: Saranya Venkatraman, Adaku Uchendu, Dongwon Lee
Abstract: The Uniform Information Density (UID) principle posits that humans prefer to spread information evenly during language production. We examine if this UID principle can help capture differences between Large Language Models (LLMs)-generated and human-generated texts. We propose GPT-who, the first psycholinguistically-inspired domain-agnostic statistical detector. This detector employs UID-based features to model the unique statistical signature of each LLM and human author for accurate detection. We evaluate our method using 4 large-scale benchmark datasets and find that GPT-who outperforms state-of-the-art detectors (both statistical- & non-statistical) such as GLTR, GPTZero, DetectGPT, OpenAI detector, and ZeroGPT by over $20$% across domains. In addition to better performance, it is computationally inexpensive and utilizes an interpretable representation of text articles. We find that GPT-who can distinguish texts generated by very sophisticated LLMs, even when the overlying text is indiscernible. UID-based measures for all datasets and code are available at https://github.com/saranya-venkatraman/gpt-who.
Authors: Xinlu Zhang, Chenxin Tian, Xianjun Yang, Lichang Chen, Zekun Li, Linda Ruth Petzold
Abstract: Instruction-finetuning (IFT) has become crucial in aligning Large Language Models (LLMs) with diverse human needs and has shown great potential in medical applications. However, previous studies mainly fine-tune LLMs on biomedical datasets with limited diversity, which often rely on benchmarks or narrow task scopes, and hence significantly limit the effectiveness on their medical instruction-following ability and generalizability. To bridge this gap, we propose creating a diverse, machine-generated medical IFT dataset, MedInstruct-52k, using GPT-4 and ChatGPT with a high-quality expert-curated seed set. We then fine-tune LLaMA-series models on the dataset to develop AlpaCare. Despite using a smaller domain-specific dataset than previous medical LLMs, AlpaCare not only demonstrates superior performance on medical applications, with up to 38.1% absolute gain over best baselines in medical free-form instruction evaluations, but also achieves 6.7% absolute gains averaged over multiple general domain benchmarks. Human evaluation further shows that AlpaCare consistently outperforms best baselines in terms of both correctness and helpfulness. We offer public access to our data, model, and codebase in https://github.com/XZhang97666/AlpaCare.
Authors: Ruyi Gan, Ziwei Wu, Renliang Sun, Junyu Lu, Xiaojun Wu, Dixiang Zhang, Kunhao Pan, Junqing He, Yuanhe Tian, Ping Yang, Qi Yang, Hao Wang, Jiaxing Zhang, Yan Song
Abstract: Various large language models (LLMs) have been proposed in recent years, including closed- and open-source ones, continually setting new records on multiple benchmarks. However, the development of LLMs still faces several issues, such as high cost of training models from scratch, and continual pre-training leading to catastrophic forgetting, etc. Although many such issues are addressed along the line of research on LLMs, an important yet practical limitation is that many studies overly pursue enlarging model sizes without comprehensively analyzing and optimizing the use of pre-training data in their learning process, as well as appropriate organization and leveraging of such data in training LLMs under cost-effective settings. In this work, we propose Ziya2, a model with 13 billion parameters adopting LLaMA2 as the foundation model, and further pre-trained on 700 billion tokens, where we focus on pre-training techniques and use data-centric optimization to enhance the learning process of Ziya2 on different stages. We define three data attributes and firstly establish data-centric scaling laws to illustrate how different data impacts LLMs. Experiments show that Ziya2 significantly outperforms other models in multiple benchmarks especially with promising results compared to representative open-source ones. Ziya2 (Base) is released at https://huggingface.co/IDEA-CCNL/Ziya2-13B-Base and https://modelscope.cn/models/Fengshenbang/Ziya2-13B-Base/summary.
URLs: https://huggingface.co/IDEA-CCNL/Ziya2-13B-Base, https://modelscope.cn/models/Fengshenbang/Ziya2-13B-Base/summary.
Authors: Zhenyu He, Zexuan Zhong, Tianle Cai, Jason D. Lee, Di He
Abstract: We introduce Retrieval-Based Speculative Decoding (REST), a novel algorithm designed to speed up language model generation. The key insight driving the development of REST is the observation that the process of text generation often includes certain common phases and patterns. Unlike previous methods that rely on a draft language model for speculative decoding, REST harnesses the power of retrieval to generate draft tokens. This method draws from the reservoir of existing knowledge, retrieving and employing relevant tokens based on the current context. Its plug-and-play nature allows for seamless integration and acceleration of any language models, all without necessitating additional training. When benchmarked on 7B and 13B language models in a single-batch setting, REST achieves a significant speedup of 1.62X to 2.36X on code or text generation. The code of REST is available at https://github.com/FasterDecoding/REST.
Authors: Tianshu Zhang, Xiang Yue, Yifei Li, Huan Sun
Abstract: Semi-structured tables are ubiquitous. There has been a variety of tasks that aim to automatically interpret, augment, and query tables. Current methods often require pretraining on tables or special model architecture design, are restricted to specific table types, or have simplifying assumptions about tables and tasks. This paper makes the first step towards developing open-source large language models (LLMs) as generalists for a diversity of table-based tasks. Towards that end, we construct TableInstruct, a new dataset with a variety of realistic tables and tasks, for instruction tuning and evaluating LLMs. We further develop the first open-source generalist model for tables, TableLlama, by fine-tuning Llama 2 (7B) with LongLoRA to address the long context challenge. We experiment under both in-domain setting and out-of-domain setting. On 7 out of 8 in-domain tasks, TableLlama achieves comparable or better performance than the SOTA for each task, despite the latter often has task-specific design. On 6 out-of-domain datasets, it achieves 5-44 absolute point gains compared with the base model, showing that training on TableInstruct enhances the model's generalizability. We open-source our dataset and trained model to boost future work on developing open generalist models for tables.
Authors: Nalin Kumar, Ond\v{r}ej Du\v{s}ek
Abstract: Linguistic entrainment, or alignment, represents a phenomenon where linguistic patterns employed by conversational participants converge to one another. While entrainment has been shown to produce a more natural user experience, most dialogue systems do not have any provisions for it. In this work, we introduce methods for achieving dialogue entrainment in a GPT-2-based end-to-end task-oriented dialogue system through the utilization of shared vocabulary. We experiment with training instance weighting, entrainment-specific loss, and additional conditioning to generate responses that align with the user. We demonstrate that all three approaches produce significantly better entrainment than the base, non-entrainment-optimized model, as confirmed by both automated and manual evaluation metrics.
Authors: Yoonsang Lee, Pranav Atreya, Xi Ye, Eunsol Choi
Abstract: In-context learning can improve the performances of knowledge-rich tasks such as question answering. In such scenarios, in-context examples trigger a language model (LM) to surface information stored in its parametric knowledge. We study how to better construct in-context example sets, based on whether the model is aware of the in-context examples. We identify 'known' examples, where models can correctly answer from their parametric knowledge, and 'unknown' ones. Our experiments show that prompting with 'unknown' examples decreases the performance, potentially as it encourages hallucination rather than searching for its parametric knowledge. Constructing an in-context example set that presents both known and unknown information performs the best across diverse settings. We perform analysis on three multi-answer question answering datasets, which allows us to further study answer set ordering strategies based on the LM's knowledge of each answer. Together, our study sheds light on how to best construct in-context example sets for knowledge-rich tasks.
Authors: Yuhan Liu, Shangbin Feng, Xiaochuang Han, Vidhisha Balachandran, Chan Young Park, Sachin Kumar, Yulia Tsvetkov
Abstract: In this work, we take a first step towards designing summarization systems that are faithful to the author's intent, not only the semantic content of the article. Focusing on a case study of preserving political perspectives in news summarization, we find that existing approaches alter the political opinions and stances of news articles in more than 50% of summaries, misrepresenting the intent and perspectives of the news authors. We thus propose P^3SUM, a diffusion model-based summarization approach controlled by political perspective classifiers. In P^3SUM, the political leaning of a generated summary is iteratively evaluated at each decoding step, and any drift from the article's original stance incurs a loss back-propagated to the embedding layers, steering the political stance of the summary at inference time. Extensive experiments on three news summarization datasets demonstrate that P^3SUM outperforms state-of-the-art summarization systems and large language models by up to 13.7% in terms of the success rate of stance preservation, with competitive performance on standard metrics of summarization quality. Our findings present a first analysis of preservation of pragmatic features in summarization, highlight the lacunae in existing summarization models -- that even state-of-the-art models often struggle to preserve author's intents -- and develop new summarization systems that are more faithful to author's perspectives.
Authors: Chunyuan Deng, Yilun Zhao, Xiangru Tang, Mark Gerstein, Arman Cohan
Abstract: Recent observations have underscored a disparity between the inflated benchmark scores and the actual performance of LLMs, raising concerns about potential contamination of evaluation benchmarks. This issue is especially critical for closed-source models and certain open-source models where training data transparency is lacking. In this paper we study data contamination by proposing two methods tailored for both open-source and proprietary LLMs. We first introduce a retrieval-based system to explore potential overlaps between evaluation benchmarks and pretraining corpora. We further present a novel investigation protocol named \textbf{T}estset \textbf{S}lot Guessing (\textit{TS-Guessing}), applicable to both open and proprietary models. This approach entails masking a wrong answer in a multiple-choice question and prompting the model to fill in the gap. Additionally, it involves obscuring an unlikely word in an evaluation example and asking the model to produce it. We find that certain commercial LLMs could surprisingly guess the missing option in various test sets. Specifically, in the TruthfulQA benchmark, we find that LLMs exhibit notable performance improvement when provided with additional metadata in the benchmark. Further, in the MMLU benchmark, ChatGPT and GPT-4 demonstrated an exact match rate of 52\% and 57\%, respectively, in guessing the missing options in benchmark test data. We hope these results underscore the need for more robust evaluation methodologies and benchmarks in the field.
Authors: Yunsheng Ma, Can Cui, Xu Cao, Wenqian Ye, Peiran Liu, Juanwu Lu, Amr Abdelraouf, Rohit Gupta, Kyungtae Han, Aniket Bera, James M. Rehg, Ziran Wang
Abstract: Autonomous driving (AD) has made significant strides in recent years. However, existing frameworks struggle to interpret and execute spontaneous user instructions, such as "overtake the car ahead." Large Language Models (LLMs) have demonstrated impressive reasoning capabilities showing potential to bridge this gap. In this paper, we present LaMPilot, a novel framework that integrates LLMs into AD systems, enabling them to follow user instructions by generating code that leverages established functional primitives. We also introduce LaMPilot-Bench, the first benchmark dataset specifically designed to quantitatively evaluate the efficacy of language model programs in AD. Adopting the LaMPilot framework, we conduct extensive experiments to assess the performance of off-the-shelf LLMs on LaMPilot-Bench. Our results demonstrate the potential of LLMs in handling diverse driving scenarios and following user instructions in driving. To facilitate further research in this area, we release our code and data at https://github.com/PurdueDigitalTwin/LaMPilot.
Authors: Dahyun Kim, Chanjun Park, Sanghoon Kim, Wonsung Lee, Wonho Song, Yunsu Kim, Hyeonwoo Kim, Yungi Kim, Hyeonju Lee, Jihoo Kim, Changbae Ahn, Seonghoon Yang, Sukyung Lee, Hyunbyung Park, Gyoungjin Gim, Mikyoung Cha, Hwalsuk Lee, Sunghun Kim
Abstract: We introduce SOLAR 10.7B, a large language model (LLM) with 10.7 billion parameters, demonstrating superior performance in various natural language processing (NLP) tasks. Inspired by recent efforts to efficiently up-scale LLMs, we present a method for scaling LLMs called depth up-scaling (DUS), which encompasses depthwise scaling and continued pretraining. In contrast to other LLM up-scaling methods that use mixture-of-experts, DUS does not require complex changes to train and inference efficiently. We show experimentally that DUS is simple yet effective in scaling up high-performance LLMs from small ones. Building on the DUS model, we additionally present SOLAR 10.7B-Instruct, a variant fine-tuned for instruction-following capabilities, surpassing Mixtral-8x7B-Instruct. SOLAR 10.7B is publicly available under the Apache 2.0 license, promoting broad access and application in the LLM field.
Authors: Meiling Tao, Xuechen Liang, Tianyu Shi, Lei Yu, Yiting Xie
Abstract: This study presents RoleCraft-GLM, an innovative framework aimed at enhancing personalized role-playing with Large Language Models (LLMs). RoleCraft-GLM addresses the key issue of lacking personalized interactions in conversational AI, and offers a solution with detailed and emotionally nuanced character portrayals. We contribute a unique conversational dataset that shifts from conventional celebrity-centric characters to diverse, non-celebrity personas, thus enhancing the realism and complexity of language modeling interactions. Additionally, our approach includes meticulous character development, ensuring dialogues are both realistic and emotionally resonant. The effectiveness of RoleCraft-GLM is validated through various case studies, highlighting its versatility and skill in different scenarios. Our framework excels in generating dialogues that accurately reflect characters' personality traits and emotions, thereby boosting user engagement. In conclusion, RoleCraft-GLM marks a significant leap in personalized AI interactions, and paves the way for more authentic and immersive AI-assisted role-playing experiences by enabling more nuanced and emotionally rich dialogues
Authors: Jianfei Xiao, Yancan Chen, Yimin Ou, Hanyi Yu, Kai Shu, Yiyong Xiao
Abstract: Large language models (LLMs) like Llama, Baichuan and Bloom models show remarkable ability with instruction fine-tuning in many natural language tasks. Nevertheless, for the dialogue summarization task, which aims to generate summaries for different roles in dialogue, most of the state-of-the-art methods conduct on small models (e.g Bart and Bert). Existing methods try to add task specified optimization on small models like adding global-local centrality score to models. In this paper, we propose an instruction fine-tuning model: Baichuan2-Sum, for role-oriented diaglouge summarization. By setting different instructions for different roles, the model can learn from the dialogue interactions and output the expected summaries. Furthermore, we applied NEFTune technique to add suitable noise during training to improve the results. The experiments demonstrate that the proposed model achieves the new state-of-the-art results on two public dialogue summarization datasets: CSDS and SAMSUM. We release our model and related codes to facilitate future studies on dialogue summarization task.
Authors: Jiacheng Liu, Sewon Min, Luke Zettlemoyer, Yejin Choi, Hannaneh Hajishirzi
Abstract: Are $n$-gram language models still relevant in this era of neural large language models (LLMs)? Our answer is yes, and we showcase their values in both text analysis and improving neural LLMs. This was done by modernizing $n$-gram LMs in two aspects. First, we train them at the same data scale as neural LLMs -- 5 trillion tokens. This is the largest $n$-gram LM ever built. Second, existing $n$-gram LMs use small $n$ which hinders their performance; we instead allow $n$ to be arbitrarily large, by introducing a new $\infty$-gram LM with backoff. Instead of pre-computing $n$-gram count tables (which would be very expensive), we develop an engine named infini-gram -- powered by suffix arrays -- that can compute $\infty$-gram (as well as $n$-gram with arbitrary $n$) probabilities with millisecond-level latency. The $\infty$-gram framework and infini-gram engine enable us to conduct many novel and interesting analyses of human-written and machine-generated text: we find that the $\infty$-gram LM has fairly high accuracy for next-token prediction (47%), and can complement neural LLMs to greatly reduce their perplexity. When analyzing machine-generated text, we also observe irregularities in the machine--$\infty$-gram agreement level with respect to the suffix length, which indicates deficiencies in neural LLM pretraining and the positional embeddings of Transformers.
Authors: Jiayuan Su, Jing Luo, Hongwei Wang, Lu Cheng
Abstract: This study aims to address the pervasive challenge of quantifying uncertainty in large language models (LLMs) without logit-access. Conformal Prediction (CP), known for its model-agnostic and distribution-free features, is a desired approach for various LLMs and data distributions. However, existing CP methods for LLMs typically assume access to the logits, which are unavailable for some API-only LLMs. In addition, logits are known to be miscalibrated, potentially leading to degraded CP performance. To tackle these challenges, we introduce a novel CP method that (1) is tailored for API-only LLMs without logit-access; (2) minimizes the size of prediction sets; and (3) ensures a statistical guarantee of the user-defined coverage. The core idea of this approach is to formulate nonconformity measures using both coarse-grained (i.e., sample frequency) and fine-grained uncertainty notions (e.g., semantic similarity). Experimental results on both close-ended and open-ended Question Answering tasks show our approach can mostly outperform the logit-based CP baselines.
Authors: Dong Yao, Asaad Alghamdi, Qingrong Xia, Xiaoye Qu, Xinyu Duan, Zhefeng Wang, Yi Zheng, Baoxing Huai, Peilun Cheng, Zhou Zhao
Abstract: Sentence semantic matching is a research hotspot in natural language processing, which is considerably significant in various key scenarios, such as community question answering, searching, chatbot, and recommendation. Since most of the advanced models directly model the semantic relevance among words between two sentences while neglecting the \textit{keywords} and \textit{intents} concepts of them, DC-Match is proposed to disentangle keywords from intents and utilizes them to optimize the matching performance. Although DC-Match is a simple yet effective method for semantic matching, it highly depends on the external NER techniques to identify the keywords of sentences, which limits the performance of semantic matching for minor languages since satisfactory NER tools are usually hard to obtain. In this paper, we propose to generally and flexibly resolve the text into multi concepts for multilingual semantic matching to liberate the model from the reliance on NER models. To this end, we devise a \underline{M}ulti-\underline{C}oncept \underline{P}arsed \underline{S}emantic \underline{M}atching framework based on the pre-trained language models, abbreviated as \textbf{MCP-SM}, to extract various concepts and infuse them into the classification tokens. We conduct comprehensive experiments on English datasets QQP and MRPC, and Chinese dataset Medical-SM. Besides, we experiment on Arabic datasets MQ2Q and XNLI, the outstanding performance further prove MCP-SM's applicability in low-resource languages.
Authors: Michal Lukasik, Harikrishna Narasimhan, Aditya Krishna Menon, Felix Yu, Sanjiv Kumar
Abstract: Large language models (LLMs) have demonstrated strong results on a range of NLP tasks. Typically, outputs are obtained via autoregressive sampling from the LLM's underlying distribution. Building on prior work on Minimum Bayes Risk Decoding, we show that this inference strategy can be suboptimal for a range of regression and scoring tasks, and associated evaluation metrics. As a remedy, we propose metric aware LLM inference: a decision theoretic approach optimizing for custom regression and scoring metrics at inference time. We report improvements over baselines on academic benchmarks and publicly available models.
Authors: Dong Yuan, Eti Rastogi, Gautam Naik, Sree Prasanna Rajagopal, Sagar Goyal, Fen Zhao, Bharath Chintagunta, Jeff Ward
Abstract: LLMs are revolutionizing NLP tasks. However, the use of the most advanced LLMs, such as GPT-4, is often prohibitively expensive for most specialized fields. We introduce HEAL, the first continuously trained 13B LLaMA2-based LLM that is purpose-built for medical conversations and measured on automated scribing. Our results demonstrate that HEAL outperforms GPT-4 and PMC-LLaMA in PubMedQA, with an accuracy of 78.4\%. It also achieves parity with GPT-4 in generating medical notes. Remarkably, HEAL surpasses GPT-4 and Med-PaLM 2 in identifying more correct medical concepts and exceeds the performance of human scribes and other comparable models in correctness and completeness.
Authors: Longzheng Wang, Xiaohan Xu, Lei Zhang, Jiarui Lu, Yongxiu Xu, Hongbo Xu, Minghao Tang, Chuang Zhang
Abstract: Automatic detection of multimodal misinformation has gained a widespread attention recently. However, the potential of powerful Large Language Models (LLMs) for multimodal misinformation detection remains underexplored. Besides, how to teach LLMs to interpret multimodal misinformation in cost-effective and accessible way is still an open question. To address that, we propose MMIDR, a framework designed to teach LLMs in providing fluent and high-quality textual explanations for their decision-making process of multimodal misinformation. To convert multimodal misinformation into an appropriate instruction-following format, we present a data augmentation perspective and pipeline. This pipeline consists of a visual information processing module and an evidence retrieval module. Subsequently, we prompt the proprietary LLMs with processed contents to extract rationales for interpreting the authenticity of multimodal misinformation. Furthermore, we design an efficient knowledge distillation approach to distill the capability of proprietary LLMs in explaining multimodal misinformation into open-source LLMs. To explore several research questions regarding the performance of LLMs in multimodal misinformation detection tasks, we construct an instruction-following multimodal misinformation dataset and conduct comprehensive experiments. The experimental findings reveal that our MMIDR exhibits sufficient detection performance and possesses the capacity to provide compelling rationales to support its assessments.
Authors: Jerry Wei, Chengrun Yang, Xinying Song, Yifeng Lu, Nathan Hu, Jie Huang, Dustin Tran, Daiyi Peng, Ruibo Liu, Da Huang, Cosmo Du, Quoc V. Le
Abstract: Large language models (LLMs) often generate content that contains factual errors when responding to fact-seeking prompts on open-ended topics. To benchmark a model's long-form factuality in open domains, we first use GPT-4 to generate LongFact, a prompt set comprising thousands of questions spanning 38 topics. We then propose that LLM agents can be used as automated evaluators for long-form factuality through a method which we call Search-Augmented Factuality Evaluator (SAFE). SAFE utilizes an LLM to break down a long-form response into a set of individual facts and to evaluate the accuracy of each fact using a multi-step reasoning process comprising sending search queries to Google Search and determining whether a fact is supported by the search results. Furthermore, we propose extending F1 score as an aggregated metric for long-form factuality. To do so, we balance the percentage of supported facts in a response (precision) with the percentage of provided facts relative to a hyperparameter representing a user's preferred response length (recall). Empirically, we demonstrate that LLM agents can outperform crowdsourced human annotators - on a set of ~16k individual facts, SAFE agrees with crowdsourced human annotators 72% of the time, and on a random subset of 100 disagreement cases, SAFE wins 76% of the time. At the same time, SAFE is more than 20 times cheaper than human annotators. We also benchmark thirteen language models on LongFact across four model families (Gemini, GPT, Claude, and PaLM-2), finding that larger language models generally achieve better long-form factuality. LongFact, SAFE, and all experimental code are available at https://github.com/google-deepmind/long-form-factuality.
URLs: https://github.com/google-deepmind/long-form-factuality.
Authors: Nedjma Ousidhoum, Shamsuddeen Hassan Muhammad, Mohamed Abdalla, Idris Abdulmumin, Ibrahim Said Ahmad, Sanchit Ahuja, Alham Fikri Aji, Vladimir Araujo, Meriem Beloucif, Christine De Kock, Oumaima Hourrane, Manish Shrivastava, Thamar Solorio, Nirmal Surange, Krishnapriya Vishnubhotla, Seid Muhie Yimam, Saif M. Mohammad
Abstract: We present the first shared task on Semantic Textual Relatedness (STR). While earlier shared tasks primarily focused on semantic similarity, we instead investigate the broader phenomenon of semantic relatedness across 14 languages: Afrikaans, Algerian Arabic, Amharic, English, Hausa, Hindi, Indonesian, Kinyarwanda, Marathi, Moroccan Arabic, Modern Standard Arabic, Punjabi, Spanish, and Telugu. These languages originate from five distinct language families and are predominantly spoken in Africa and Asia -- regions characterised by the relatively limited availability of NLP resources. Each instance in the datasets is a sentence pair associated with a score that represents the degree of semantic textual relatedness between the two sentences. Participating systems were asked to rank sentence pairs by their closeness in meaning (i.e., their degree of semantic relatedness) in the 14 languages in three main tracks: (a) supervised, (b) unsupervised, and (c) crosslingual. The task attracted 163 participants. We received 70 submissions in total (across all tasks) from 51 different teams, and 38 system description papers. We report on the best-performing systems as well as the most common and the most effective approaches for the three different tracks.
Authors: Manjeet Yadav, Nilesh Kumar Sahu, Mudita Chaturvedi, Snehil Gupta, Haroon R Lone
Abstract: Improving mental health support in developing countries is a pressing need. One potential solution is the development of scalable, automated systems to conduct diagnostic screenings, which could help alleviate the burden on mental health professionals. In this work, we evaluate several state-of-the-art Large Language Models (LLMs), with and without fine-tuning, on our custom dataset for generating concise summaries from mental state examinations. We rigorously evaluate four different models for summary generation using established ROUGE metrics and input from human evaluators. The results highlight that our top-performing fine-tuned model outperforms existing models, achieving ROUGE-1 and ROUGE-L values of 0.810 and 0.764, respectively. Furthermore, we assessed the fine-tuned model's generalizability on a publicly available D4 dataset, and the outcomes were promising, indicating its potential applicability beyond our custom dataset.
Authors: Tenghao Huang, Dongwon Jung, Muhao Chen
Abstract: Recent advancements in integrating external tools with Large Language Models (LLMs) have opened new frontiers, with applications in mathematical reasoning, code generators, and smart assistants. However, existing methods, relying on simple one-time retrieval strategies, fall short on effectively and accurately shortlisting relevant tools. This paper introduces a novel PLUTO (Planning, Learning, and Understanding for TOols) approach, encompassing `Plan-and-Retrieve (P&R)` and `Edit-and-Ground (E&G)` paradigms. The P&R paradigm consists of a neural retrieval module for shortlisting relevant tools and an LLM-based query planner that decomposes complex queries into actionable tasks, enhancing the effectiveness of tool utilization. The E&G paradigm utilizes LLMs to enrich tool descriptions based on user scenarios, bridging the gap between user queries and tool functionalities. Experiment results demonstrate that these paradigms significantly improve the recall and NDCG in tool retrieval tasks, significantly surpassing current state-of-the-art models.
Authors: Yujuan Fu, Giridhar Kaushik Ramachandran, Nicholas J Dobbins, Namu Park, Michael Leu, Abby R. Rosenberg, Kevin Lybarger, Fei Xia, Ozlem Uzuner, Meliha Yetisgen
Abstract: Social determinants of health (SDoH) play a critical role in shaping health outcomes, particularly in pediatric populations where interventions can have long-term implications. SDoH are frequently studied in the Electronic Health Record (EHR), which provides a rich repository for diverse patient data. In this work, we present a novel annotated corpus, the Pediatric Social History Annotation Corpus (PedSHAC), and evaluate the automatic extraction of detailed SDoH representations using fine-tuned and in-context learning methods with Large Language Models (LLMs). PedSHAC comprises annotated social history sections from 1,260 clinical notes obtained from pediatric patients within the University of Washington (UW) hospital system. Employing an event-based annotation scheme, PedSHAC captures ten distinct health determinants to encompass living and economic stability, prior trauma, education access, substance use history, and mental health with an overall annotator agreement of 81.9 F1. Our proposed fine-tuning LLM-based extractors achieve high performance at 78.4 F1 for event arguments. In-context learning approaches with GPT-4 demonstrate promise for reliable SDoH extraction with limited annotated examples, with extraction performance at 82.3 F1 for event triggers.
Authors: Frank Palma Gomez, Ramon Sanabria, Yun-hsuan Sung, Daniel Cer, Siddharth Dalmia, Gustavo Hernandez Abrego
Abstract: Large language models (LLMs) are trained on text-only data that go far beyond the languages with paired speech and text data. At the same time, Dual Encoder (DE) based retrieval systems project queries and documents into the same embedding space and have demonstrated their success in retrieval and bi-text mining. To match speech and text in many languages, we propose using LLMs to initialize multi-modal DE retrieval systems. Unlike traditional methods, our system doesn't require speech data during LLM pre-training and can exploit LLM's multilingual text understanding capabilities to match speech and text in languages unseen during retrieval training. Our multi-modal LLM-based retrieval system is capable of matching speech and text in 102 languages despite only training on 21 languages. Our system outperforms previous systems trained explicitly on all 102 languages. We achieve a 10% absolute improvement in Recall@1 averaged across these languages. Additionally, our model demonstrates cross-lingual speech and text matching, which is further enhanced by readily available machine translation data.
Authors: Xuechen Liang, Meiling Tao, Tianyu Shi, Yiting Xie
Abstract: Open large language models (LLMs) have significantly advanced the field of natural language processing, showcasing impressive performance across various tasks.Despite the significant advancements in LLMs, their effective operation still relies heavily on human input to accurately guide the dialogue flow, with agent tuning being a crucial optimization technique that involves human adjustments to the model for better response to such guidance.Addressing this dependency, our work introduces the TinyAgent model, trained on a meticulously curated high-quality dataset. We also present the Collaborative Multi-Agent Tuning (CMAT) framework, an innovative system designed to augment language agent capabilities through adaptive weight updates based on environmental feedback. This framework fosters collaborative learning and real-time adaptation among multiple intelligent agents, enhancing their context-awareness and long-term memory. In this research, we propose a new communication agent framework that integrates multi-agent systems with environmental feedback mechanisms, offering a scalable method to explore cooperative behaviors. Notably, our TinyAgent-7B model exhibits performance on par with GPT-3.5, despite having fewer parameters, signifying a substantial improvement in the efficiency and effectiveness of LLMs.
Authors: Enmin Zhu, Jerome Yen
Abstract: This paper explores the intersection of Natural Language Processing (NLP) and financial analysis, focusing on the impact of sentiment analysis in stock price prediction. We employ BERTopic, an advanced NLP technique, to analyze the sentiment of topics derived from stock market comments. Our methodology integrates this sentiment analysis with various deep learning models, renowned for their effectiveness in time series and stock prediction tasks. Through comprehensive experiments, we demonstrate that incorporating topic sentiment notably enhances the performance of these models. The results indicate that topics in stock market comments provide implicit, valuable insights into stock market volatility and price trends. This study contributes to the field by showcasing the potential of NLP in enriching financial analysis and opens up avenues for further research into real-time sentiment analysis and the exploration of emotional and contextual aspects of market sentiment. The integration of advanced NLP techniques like BERTopic with traditional financial analysis methods marks a step forward in developing more sophisticated tools for understanding and predicting market behaviors.
Authors: Tianle Li, Ge Zhang, Quy Duc Do, Xiang Yue, Wenhu Chen
Abstract: Large Language Models (LLMs) have made significant strides in handling long sequences exceeding 32K tokens. However, their performance evaluation has largely been confined to metrics like perplexity and synthetic tasks, which may not fully capture their abilities in more nuanced, real-world scenarios. This study introduces a specialized benchmark (LongICLBench) focusing on long in-context learning within the realm of extreme-label classification. We meticulously selected six datasets with a label range spanning 28 to 174 classes covering different input (few-shot demonstration) lengths from 2K to 50K tokens. Our benchmark requires LLMs to comprehend the entire input to recognize the massive label spaces to make correct predictions. We evaluate 13 long-context LLMs on our benchmarks. We find that the long-context LLMs perform relatively well on less challenging tasks with shorter demonstration lengths by effectively utilizing the long context window. However, on the most challenging task Discovery with 174 labels, all the LLMs struggle to understand the task definition, thus reaching a performance close to zero. This suggests a notable gap in current LLM capabilities for processing and understanding long, context-rich sequences. Further analysis revealed a tendency among models to favor predictions for labels presented toward the end of the sequence. Their ability to reason over multiple pieces in the long sequence is yet to be improved. Our study reveals that long context understanding and reasoning is still a challenging task for the existing LLMs. We believe LongICLBench could serve as a more realistic evaluation for the future long-context LLMs.
Authors: Thinh Hung Truong, Yulia Otmakhova, Karin Verspoor, Trevor Cohn, Timothy Baldwin
Abstract: In this work, we measure the impact of affixal negation on modern English large language models (LLMs). In affixal negation, the negated meaning is expressed through a negative morpheme, which is potentially challenging for LLMs as their tokenizers are often not morphologically plausible. We conduct extensive experiments using LLMs with different subword tokenization methods, which lead to several insights on the interaction between tokenization performance and negation sensitivity. Despite some interesting mismatches between tokenization accuracy and negation detection performance, we show that models can, on the whole, reliably recognize the meaning of affixal negation.
Authors: Nishat Raihan, Dhiman Goswami, Sadiya Sayara Chowdhury Puspo, Christian Newman, Tharindu Ranasinghe, Marcos Zampieri
Abstract: Recent advances in AI, machine learning, and NLP have led to the development of a new generation of Large Language Models (LLMs) that are trained on massive amounts of data and often have trillions of parameters. Commercial applications (e.g., ChatGPT) have made this technology available to the general public, thus making it possible to use LLMs to produce high-quality texts for academic and professional purposes. Schools and universities are aware of the increasing use of AI-generated content by students and they have been researching the impact of this new technology and its potential misuse. Educational programs in Computer Science (CS) and related fields are particularly affected because LLMs are also capable of generating programming code in various programming languages. To help understand the potential impact of publicly available LLMs in CS education, we introduce CSEPrompts, a framework with hundreds of programming exercise prompts and multiple-choice questions retrieved from introductory CS and programming courses. We also provide experimental results on CSEPrompts to evaluate the performance of several LLMs with respect to generating Python code and answering basic computer science and programming questions.
Authors: Maike Behrendt, Stefan Sylvius Wagner, Marc Ziegele, Lena Wilms, Anke Stoll, Dominique Heinbach, Stefan Harmeling
Abstract: Measuring the quality of contributions in political online discussions is crucial in deliberation research and computer science. Research has identified various indicators to assess online discussion quality, and with deep learning advancements, automating these measures has become feasible. While some studies focus on analyzing specific quality indicators, a comprehensive quality score incorporating various deliberative aspects is often preferred. In this work, we introduce AQuA, an additive score that calculates a unified deliberative quality score from multiple indices for each discussion post. Unlike other singular scores, AQuA preserves information on the deliberative aspects present in comments, enhancing model transparency. We develop adapter models for 20 deliberative indices, and calculate correlation coefficients between experts' annotations and the perceived deliberativeness by non-experts to weigh the individual indices into a single deliberative score. We demonstrate that the AQuA score can be computed easily from pre-trained adapters and aligns well with annotations on other datasets that have not be seen during training. The analysis of experts' vs. non-experts' annotations confirms theoretical findings in the social science literature.
Authors: Lingbing Guo, Zhuo Chen, Jiaoyan Chen, Yichi Zhang, Zequn Sun, Zhongpo Bo, Yin Fang, Xiaoze Liu, Huajun Chen, Wen Zhang
Abstract: Graph neural network (GNN)-based methods have demonstrated remarkable performance in various knowledge graph (KG) tasks. However, most existing approaches rely on observing all entities during training, posing a challenge in real-world knowledge graphs where new entities emerge frequently. To address this limitation, we introduce Decentralized Attention Network (DAN). DAN leverages neighbor context as the query vector to score the neighbors of an entity, thereby distributing the entity semantics only among its neighbor embeddings. To effectively train a DAN, we introduce self-distillation, a technique that guides the network in generating desired representations. Theoretical analysis validates the effectiveness of our approach. We implement an end-to-end framework and conduct extensive experiments to evaluate our method, showcasing competitive performance on conventional entity alignment and entity prediction tasks. Furthermore, our method significantly outperforms existing methods in open-world settings.
Authors: Jiangyan Yi, Chenglong Wang, Jianhua Tao, Chu Yuan Zhang, Cunhang Fan, Zhengkun Tian, Haoxin Ma, Ruibo Fu
Abstract: Many datasets have been designed to further the development of fake audio detection. However, fake utterances in previous datasets are mostly generated by altering timbre, prosody, linguistic content or channel noise of original audio. These datasets leave out a scenario, in which the acoustic scene of an original audio is manipulated with a forged one. It will pose a major threat to our society if some people misuse the manipulated audio with malicious purpose. Therefore, this motivates us to fill in the gap. This paper proposes such a dataset for scene fake audio detection named SceneFake, where a manipulated audio is generated by only tampering with the acoustic scene of an real utterance by using speech enhancement technologies. Some scene fake audio detection benchmark results on the SceneFake dataset are reported in this paper. In addition, an analysis of fake attacks with different speech enhancement technologies and signal-to-noise ratios are presented in this paper. The results indicate that scene fake utterances cannot be reliably detected by baseline models trained on the ASVspoof 2019 dataset. Although these models perform well on the SceneFake training set and seen testing set, their performance is poor on the unseen test set. The dataset (https://zenodo.org/record/7663324#.Y_XKMuPYuUk) and benchmark source codes (https://github.com/ADDchallenge/SceneFake) are publicly available.
URLs: https://zenodo.org/record/7663324, https://github.com/ADDchallenge/SceneFake)
Authors: Riccardo Rende, Federica Gerace, Alessandro Laio, Sebastian Goldt
Abstract: Transformers are neural networks that revolutionized natural language processing and machine learning. They process sequences of inputs, like words, using a mechanism called self-attention, which is trained via masked language modeling (MLM). In MLM, a word is randomly masked in an input sequence, and the network is trained to predict the missing word. Despite the practical success of transformers, it remains unclear what type of data distribution self-attention can learn efficiently. Here, we show analytically that if one decouples the treatment of word positions and embeddings, a single layer of self-attention learns the conditionals of a generalized Potts model with interactions between sites and Potts colors. Moreover, we show that training this neural network is exactly equivalent to solving the inverse Potts problem by the so-called pseudo-likelihood method, well known in statistical physics. Using this mapping, we compute the generalization error of self-attention in a model scenario analytically using the replica method.
Authors: Lei Wang, Chen Ma, Xueyang Feng, Zeyu Zhang, Hao Yang, Jingsen Zhang, Zhiyuan Chen, Jiakai Tang, Xu Chen, Yankai Lin, Wayne Xin Zhao, Zhewei Wei, Ji-Rong Wen
Abstract: Autonomous agents have long been a prominent research focus in both academic and industry communities. Previous research in this field often focuses on training agents with limited knowledge within isolated environments, which diverges significantly from human learning processes, and thus makes the agents hard to achieve human-like decisions. Recently, through the acquisition of vast amounts of web knowledge, large language models (LLMs) have demonstrated remarkable potential in achieving human-level intelligence. This has sparked an upsurge in studies investigating LLM-based autonomous agents. In this paper, we present a comprehensive survey of these studies, delivering a systematic review of the field of LLM-based autonomous agents from a holistic perspective. More specifically, we first discuss the construction of LLM-based autonomous agents, for which we propose a unified framework that encompasses a majority of the previous work. Then, we present a comprehensive overview of the diverse applications of LLM-based autonomous agents in the fields of social science, natural science, and engineering. Finally, we delve into the evaluation strategies commonly used for LLM-based autonomous agents. Based on the previous studies, we also present several challenges and future directions in this field. To keep track of this field and continuously update our survey, we maintain a repository of relevant references at https://github.com/Paitesanshi/LLM-Agent-Survey.
Authors: Furui Cheng, Vil\'em Zouhar, Simran Arora, Mrinmaya Sachan, Hendrik Strobelt, Mennatallah El-Assady
Abstract: Large Language Models (LLMs) are notorious for blending fact with fiction and generating non-factual content, known as hallucinations. To address this challenge, we propose an interactive system that helps users gain insight into the reliability of the generated text. Our approach is based on the idea that the self-consistency of multiple samples generated by the same LLM relates to its confidence in individual claims in the generated texts. Using this idea, we design RELIC, an interactive system that enables users to investigate and verify semantic-level variations in multiple long-form responses. This allows users to recognize potentially inaccurate information in the generated text and make necessary corrections. From a user study with ten participants, we demonstrate that our approach helps users better verify the reliability of the generated text. We further summarize the design implications and lessons learned from this research for future studies of reliable human-LLM interactions.
Authors: Alex Mallen, Madeline Brumley, Julia Kharchenko, Nora Belrose
Abstract: Eliciting Latent Knowledge (ELK) aims to find patterns in a capable neural network's activations that robustly track the true state of the world, especially in hard-to-verify cases where the model's output is untrusted. To further ELK research, we introduce 12 datasets and a corresponding suite of "quirky" language models (LMs) that are finetuned to make systematic errors when answering questions if and only if the keyword "Bob" is present in the prompt. We find that, especially in middle layers, linear probes usually report an LM's knowledge independently of what the LM outputs, enabling us to elicit the correct answer despite the model's untruthful output. The best probing method (logistic regression on contrast pairs) recovers 89% of the gap in AUROC between truthful and untruthful contexts, and 75% for questions harder than those used to train the probe. We also find that a mechanistic anomaly detection approach can flag untruthful behavior with 0.95 AUROC. Our results show promise for eliciting reliable knowledge from capable but untrusted models, and facilitates future research empirically investigating ELK methods.
Authors: Georgios Fatouros, Konstantinos Metaxas, John Soldatos, Dimosthenis Kyriazis
Abstract: This paper introduces MarketSenseAI, an innovative framework leveraging GPT-4's advanced reasoning for selecting stocks in financial markets. By integrating Chain of Thought and In-Context Learning, MarketSenseAI analyzes diverse data sources, including market trends, news, fundamentals, and macroeconomic factors, to emulate expert investment decision-making. The development, implementation, and validation of the framework are elaborately discussed, underscoring its capability to generate actionable and interpretable investment signals. A notable feature of this work is employing GPT-4 both as a predictive mechanism and signal evaluator, revealing the significant impact of the AI-generated explanations on signal accuracy, reliability and acceptance. Through empirical testing on the competitive S&P 100 stocks over a 15-month period, MarketSenseAI demonstrated exceptional performance, delivering excess alpha of 10% to 30% and achieving a cumulative return of up to 72% over the period, while maintaining a risk profile comparable to the broader market. Our findings highlight the transformative potential of Large Language Models in financial decision-making, marking a significant leap in integrating generative AI into financial analytics and investment strategies.
Authors: Xiaoyue Wang, Jianyou Wang, Weili Cao, Kaicheng Wang, Ramamohan Paturi, Leon Bergen
Abstract: We present the Benchmark of Information Retrieval (IR) tasks with Complex Objectives (BIRCO). BIRCO evaluates the ability of IR systems to retrieve documents given multi-faceted user objectives. The benchmark's complexity and compact size make it suitable for evaluating large language model (LLM)-based information retrieval systems. We present a modular framework for investigating factors that may influence LLM performance on retrieval tasks, and identify a simple baseline model which matches or outperforms existing approaches and more complex alternatives. No approach achieves satisfactory performance on all benchmark tasks, suggesting that stronger models and new retrieval protocols are necessary to address complex user needs.
Authors: Zhouhong Gu, Xiaoxuan Zhu, Haoran Guo, Lin Zhang, Yin Cai, Hao Shen, Jiangjie Chen, Zheyu Ye, Yifei Dai, Yan Gao, Yao Hu, Hongwei Feng, Yanghua Xiao
Abstract: Language significantly influences the formation and evolution of Human emergent behavior, which is crucial in understanding collective intelligence within human societies. Considering that the study of how language affects human behavior needs to put it into the dynamic scenarios in which it is used, we introduce AgentGroupChat in this paper, a simulation that delves into the complex role of language in shaping collective behavior through interactive debate scenarios. Central to this simulation are characters engaging in dynamic conversation interactions. To enable simulation, we introduce the Verbal Strategist Agent, utilizing large language models to enhance interaction strategies by incorporating elements of persona and action. We set four narrative scenarios based on AgentGroupChat to demonstrate the simulation's capacity to mimic complex language use in group dynamics. Evaluations focus on aligning agent behaviors with human expectations and the emergence of collective behaviors within the simulation. Results reveal that emergent behaviors materialize from a confluence of factors: a conducive environment for extensive information exchange, characters with diverse traits, high linguistic comprehension, and strategic adaptability. During discussions on ``the impact of AI on humanity'' in AgentGroupChat simulation, philosophers commonly agreed that ``AI could enhance societal welfare with judicious limitations'' and even come to a conclusion that ``the essence of true intelligence encompasses understanding the necessity to constrain self abilities''. Additionally, in the competitive domain of casting for primary roles in films in AgentGroupChat, certain actors were ready to reduce their remuneration or accept lesser roles, motivated by their deep-seated desire to contribute to the project.
Authors: Matyas Juhasz, Tina Marchand, Roshan Melwani, Kalyan Dutia, Sarah Goodenough, Harrison Pim, Henry Franks
Abstract: Quantified policy targets are a fundamental element of climate policy, typically characterised by domain-specific and technical language. Current methods for curating comprehensive views of global climate policy targets entail significant manual effort. At present there are few scalable methods for extracting climate targets from national laws or policies, which limits policymakers' and researchers' ability to (1) assess private and public sector alignment with global goals and (2) inform policy decisions. In this paper we present an approach for extracting mentions of climate targets from national laws and policies. We create an expert-annotated dataset identifying three categories of target ('Net Zero', 'Reduction' and 'Other' (e.g. renewable energy targets)) and train a classifier to reliably identify them in text. We investigate bias and equity impacts related to our model and identify specific years and country names as problematic features. Finally, we investigate the characteristics of the dataset produced by running this classifier on the Climate Policy Radar (CPR) dataset of global national climate laws and policies and UNFCCC submissions, highlighting the potential of automated and scalable data collection for existing climate policy databases and supporting further research. Our work represents a significant upgrade in the accessibility of these key climate policy elements for policymakers and researchers. We publish our model at https://huggingface.co/ClimatePolicyRadar/national-climate-targets and related dataset at https://huggingface.co/datasets/ClimatePolicyRadar/national-climate-targets.
URLs: https://huggingface.co/ClimatePolicyRadar/national-climate-targets, https://huggingface.co/datasets/ClimatePolicyRadar/national-climate-targets.