Authors: Alhassan Mabrouk, Rebeca P. Díaz-Redondo, Mohammed Kayed
E-Commerce (EC) websites provide a large amount of useful information that exceed human cognitive processing ability. In order to help customers in comparing alternatives when buying a product, previous studies designed opinion summarization systems based on customer reviews. They ignored templates' information provided by manufacturers, although these descriptive information have much product aspects or characteristics. Therefore, this paper proposes a methodology coined as SEOpinion (Summa-rization and Exploration of Opinions) which provides a summary for the product aspects and spots opinion(s) regarding them, using a combination of templates' information with the customer reviews in two main phases. First, the Hierarchical Aspect Extraction (HAE) phase creates a hierarchy of product aspects from the template. Subsequently, the Hierarchical Aspect-based Opinion Summarization (HAOS) phase enriches this hierarchy with customers' opinions; to be shown to other potential buyers. To test the feasibility of using Deep Learning-based BERT techniques with our approach, we have created a corpus by gathering information from the top five EC websites for laptops. The experimental results show that Recurrent Neural Network (RNN) achieves better results (77.4% and 82.6% in terms of F1-measure for the first and second phase) than the Convolutional Neural Network (CNN) and the Support Vector Machine (SVM) technique.
Authors: Hanwen Ye, Tatiana Moreno, Adrianne Alpern, Louis Ehwerhemuepha, Annie Qu
Mental health diseases affect children's lives and well-beings which have received increased attention since the COVID-19 pandemic. Analyzing psychiatric clinical notes with topic models is critical to evaluate children's mental status over time. However, few topic models are built for longitudinal settings, and they fail to keep consistent topics and capture temporal trajectories for each document. To address these challenges, we develop a longitudinal topic model with time-invariant topics and individualized temporal dependencies on the evolving document metadata. Our model preserves the semantic meaning of discovered topics over time and incorporates heterogeneity among documents. In particular, when documents can be categorized, we propose an unsupervised topics learning approach to maximize topic heterogeneity across different document groups. We also present an efficient variational optimization procedure adapted for the multistage longitudinal setting. In this case study, we apply our method to the psychiatric clinical notes from a large tertiary pediatric hospital in Southern California and achieve a 38% increase in the overall coherence of extracted topics. Our real data analysis reveals that children tend to express more negative emotions during state shutdowns and more positive when schools reopen. Furthermore, it suggests that sexual and gender minority (SGM) children display more pronounced reactions to major COVID-19 events and a greater sensitivity to vaccine-related news than non-SGM children. This study examines the progression of children's mental health during the pandemic and offers clinicians valuable insights to recognize the disparities in children's mental health related to their sexual and gender identities.
Authors: Ben Snyder, Marius Moisescu, Muhammad Bilal Zafar
While large language models (LLMs) have taken great strides towards helping humans with a plethora of tasks like search and summarization, hallucinations remain a major impediment towards gaining user trust. The fluency and coherence of model generations even when hallucinating makes it difficult to detect whether or not a model is hallucinating. In this work, we explore if the artifacts associated with the model generations can provide hints that the generation will contain hallucinations. Specifically, we probe LLMs at 1) the inputs via Integrated Gradients based token attribution, 2) the outputs via the Softmax probabilities, and 3) the internal state via self-attention and fully-connected layer activations for signs of hallucinations on open-ended question answering tasks. Our results show that the distributions of these artifacts differ between hallucinated and non-hallucinated generations. Building on this insight, we train binary classifiers that use these artifacts as input features to classify model generations into hallucinations and non-hallucinations. These hallucination classifiers achieve up to 0.80 AUROC. We further show that tokens preceding a hallucination can predict the subsequent hallucination before it occurs.
Authors: Xiaodan Zhang, Sandeep Vemulapalli, Nabasmita Talukdar, Sumyeong Ahn, Jiankun Wang, Han Meng, Sardar Mehtab Bin Murtaza, Aakash Ajay Dave, Dmitry Leshchiner, Dimitri F. Joseph, Martin Witteveen-Lane, Dave Chesla, Jiayu Zhou, Bin Chen
This study assesses the ability of state-of-the-art large language models (LLMs) including GPT-3.5, GPT-4, Falcon, and LLaMA 2 to identify patients with mild cognitive impairment (MCI) from discharge summaries and examines instances where the models' responses were misaligned with their reasoning. Utilizing the MIMIC-IV v2.2 database, we focused on a cohort aged 65 and older, verifying MCI diagnoses against ICD codes and expert evaluations. The data was partitioned into training, validation, and testing sets in a 7:2:1 ratio for model fine-tuning and evaluation, with an additional metastatic cancer dataset from MIMIC III used to further assess reasoning consistency. GPT-4 demonstrated superior interpretative capabilities, particularly in response to complex prompts, yet displayed notable response-reasoning inconsistencies. In contrast, open-source models like Falcon and LLaMA 2 achieved high accuracy but lacked explanatory reasoning, underscoring the necessity for further research to optimize both performance and interpretability. The study emphasizes the significance of prompt engineering and the need for further exploration into the unexpected reasoning-response misalignment observed in GPT-4. The results underscore the promise of incorporating LLMs into healthcare diagnostics, contingent upon methodological advancements to ensure accuracy and clinical coherence of AI-generated outputs, thereby improving the trustworthiness of LLMs for medical decision-making.
Authors: Zirong Chen, Xutong Sun, Yuanhe Li, Meiyi Ma
Emergency and non-emergency response systems are essential services provided by local governments and critical to protecting lives, the environment, and property. The effective handling of (non-)emergency calls is critical for public safety and well-being. By reducing the burden through non-emergency callers, residents in critical need of assistance through 911 will receive a fast and effective response. Collaborating with the Department of Emergency Communications (DEC) in Nashville, we analyzed 11,796 non-emergency call recordings and developed Auto311, the first automated system to handle 311 non-emergency calls, which (1) effectively and dynamically predicts ongoing non-emergency incident types to generate tailored case reports during the call; (2) itemizes essential information from dialogue contexts to complete the generated reports; and (3) strategically structures system-caller dialogues with optimized confidence. We used real-world data to evaluate the system's effectiveness and deployability. The experimental results indicate that the system effectively predicts incident type with an average F-1 score of 92.54%. Moreover, the system successfully itemizes critical information from relevant contexts to complete reports, evincing a 0.93 average consistency score compared to the ground truth. Additionally, emulations demonstrate that the system effectively decreases conversation turns as the utterance size gets more extensive and categorizes the ongoing call with 94.49% mean accuracy.
Authors: Zhaojian Yu, Xin Zhang, Ning Shang, Yangyu Huang, Can Xu, Yishujie Zhao, Wenxiang Hu, Qiufeng Yin
Recent work demonstrates that, after being fine-tuned on a high-quality instruction dataset, the resulting model can obtain impressive capabilities to address a wide range of tasks. However, existing methods for instruction data generation often produce duplicate data and are not controllable enough on data quality. In this paper, we extend the generalization of instruction tuning by classifying the instruction data to 4 code-related tasks and propose a LLM-based Generator-Discriminator data process framework to generate diverse, high-quality instruction data from open source code. Hence, we introduce CodeOcean, a dataset comprising 20,000 instruction instances across 4 universal code-related tasks,which is aimed at augmenting the effectiveness of instruction tuning and improving the generalization ability of fine-tuned model. Subsequently, we present WaveCoder, a fine-tuned Code LLM with Widespread And Versatile Enhanced instruction tuning. This model is specifically designed for enhancing instruction tuning of Code Language Models (LLMs). Our experiments demonstrate that Wavecoder models outperform other open-source models in terms of generalization ability across different code-related tasks at the same level of fine-tuning scale. Moreover, Wavecoder exhibits high efficiency in previous code generation tasks. This paper thus offers a significant contribution to the field of instruction data generation and fine-tuning models, providing new insights and tools for enhancing performance in code-related tasks.
Authors: Jingwei Yi, Yueqi Xie, Bin Zhu, Keegan Hines, Emre Kiciman, Guangzhong Sun, Xing Xie, Fangzhao Wu
Recent remarkable advancements in large language models (LLMs) have led to their widespread adoption in various applications. A key feature of these applications is the combination of LLMs with external content, where user instructions and third-party content are combined to create prompts for LLM processing. These applications, however, are vulnerable to indirect prompt injection attacks, where malicious instructions embedded within external content compromise LLM's output, causing their responses to deviate from user expectations. Despite the discovery of this security issue, no comprehensive analysis of indirect prompt injection attacks on different LLMs is available due to the lack of a benchmark. Furthermore, no effective defense has been proposed.
In this work, we introduce the first benchmark, BIPIA, to measure the robustness of various LLMs and defenses against indirect prompt injection attacks. Our experiments reveal that LLMs with greater capabilities exhibit more vulnerable to indirect prompt injection attacks for text tasks, resulting in a higher ASR. We hypothesize that indirect prompt injection attacks are mainly due to the LLMs' inability to distinguish between instructions and external content. Based on this conjecture, we propose four black-box methods based on prompt learning and a white-box defense methods based on fine-tuning with adversarial training to enable LLMs to distinguish between instructions and external content and ignore instructions in the external content. Our experimental results show that our black-box defense methods can effectively reduce ASR but cannot completely thwart indirect prompt injection attacks, while our white-box defense method can reduce ASR to nearly zero with little adverse impact on the LLM's performance on general tasks. We hope that our benchmark and defenses can inspire future work in this important area.
Authors: Yang Lu, Jordan Yu, Shou-Hsuan Stephen Huang
This study explores the idea of AI Personality or AInality suggesting that Large Language Models (LLMs) exhibit patterns similar to human personalities. Assuming that LLMs share these patterns with humans, we investigate using human-centered psychometric tests such as the Myers-Briggs Type Indicator (MBTI), Big Five Inventory (BFI), and Short Dark Triad (SD3) to identify and confirm LLM personality types. By introducing role-play prompts, we demonstrate the adaptability of LLMs, showing their ability to switch dynamically between different personality types. Using projective tests, such as the Washington University Sentence Completion Test (WUSCT), we uncover hidden aspects of LLM personalities that are not easily accessible through direct questioning. Projective tests allowed for a deep exploration of LLMs cognitive processes and thought patterns and gave us a multidimensional view of AInality. Our machine learning analysis revealed that LLMs exhibit distinct AInality traits and manifest diverse personality types, demonstrating dynamic shifts in response to external instructions. This study pioneers the application of projective tests on LLMs, shedding light on their diverse and adaptable AInality traits.
Authors: Zhongyang Guo, Guanran Jiang, Zhongdan Zhang, Peng Li, Zhefeng Wang, Yinchun Wang
This paper introduces "Shai" a 10B level large language model specifically designed for the asset management industry, built upon an open-source foundational model. With continuous pre-training and fine-tuning using a targeted corpus, Shai demonstrates enhanced performance in tasks relevant to its domain, outperforming baseline models. Our research includes the development of an innovative evaluation framework, which integrates professional qualification exams, tailored tasks, open-ended question answering, and safety assessments, to comprehensively assess Shai's capabilities. Furthermore, we discuss the challenges and implications of utilizing large language models like GPT-4 for performance assessment in asset management, suggesting a combination of automated evaluation and human judgment. Shai's development, showcasing the potential and versatility of 10B-level large language models in the financial sector with significant performance and modest computational requirements, hopes to provide practical insights and methodologies to assist industry peers in their similar endeavors.
Authors: Sergi Blanco-Cuaresma, Ioana Ciucă, Alberto Accomazzi, Michael J. Kurtz, Edwin A. Henneken, Kelly E. Lockhart, Felix Grezes, Thomas Allen, Golnaz Shapurian, Carolyn S. Grant, Donna M. Thompson, Timothy W. Hostetler, Matthew R. Templeton, Shinyi Chen, Jennifer Koch, Taylor Jacovich, Daniel Chivvis, Fernanda de Macedo Alves, Jean-Claude Paquin, Jennifer Bartlett, Mugdha Polimera, Stephanie Jarmak
Open-source Large Language Models enable projects such as NASA SciX (i.e., NASA ADS) to think out of the box and try alternative approaches for information retrieval and data augmentation, while respecting data copyright and users' privacy. However, when large language models are directly prompted with questions without any context, they are prone to hallucination. At NASA SciX we have developed an experiment where we created semantic vectors for our large collection of abstracts and full-text content, and we designed a prompt system to ask questions using contextual chunks from our system. Based on a non-systematic human evaluation, the experiment shows a lower degree of hallucination and better responses when using Retrieval Augmented Generation. Further exploration is required to design new features and data augmentation processes at NASA SciX that leverages this technology while respecting the high level of trust and quality that the project holds.
Authors: Sean Memery, Mirella Lapata, Kartic Subr
Recent developments in large-scale machine learning models for general-purpose understanding, translation and generation of language are driving impact across a variety of sectors including medicine, robotics, and scientific discovery. The strength of such Large Language Models (LLMs) stems from the large corpora that they are trained with. While this imbues them with a breadth of capabilities, they have been found unsuitable for some specific types of problems such as advanced mathematics. In this paper, we highlight the inability of LLMs to reason about physics tasks. We demonstrate that their ability to infer parameters of physical systems can be improved, without retraining, by augmenting their context with feedback from physical simulation.
Authors: Liyi Zhang, R. Thomas McCoy, Theodore R. Sumers, Jian-Qiao Zhu, Thomas L. Griffiths
Large language models (LLMs) can produce long, coherent passages of text, suggesting that LLMs, although trained on next-word prediction, must represent the latent structure that characterizes a document. Prior work has found that internal representations of LLMs encode one aspect of latent structure, namely syntax; here we investigate a complementary aspect, namely the document's topic structure. We motivate the hypothesis that LLMs capture topic structure by connecting LLM optimization to implicit Bayesian inference. De Finetti's theorem shows that exchangeable probability distributions can be represented as a mixture with respect to a latent generating distribution. Although text is not exchangeable at the level of syntax, exchangeability is a reasonable starting assumption for topic structure. We thus hypothesize that predicting the next token in text will lead LLMs to recover latent topic distributions. We examine this hypothesis using Latent Dirichlet Allocation (LDA), an exchangeable probabilistic topic model, as a target, and we show that the representations formed by LLMs encode both the topics used to generate synthetic data and those used to explain natural corpus data.
Authors: Xingfang Wu, Eric Laufer, Heng Li, Foutse Khomh, Santhosh Srinivasan, Jayden Luo
With the rapid growth of the developer community, the amount of posts on online technical forums has been growing rapidly, which poses difficulties for users to filter useful posts and find important information. Tags provide a concise feature dimension for users to locate their interested posts and for search engines to index the most relevant posts according to the queries. However, most tags are only focused on the technical perspective (e.g., program language, platform, tool). In most cases, forum posts in online developer communities reveal the author's intentions to solve a problem, ask for advice, share information, etc. The modeling of the intentions of posts can provide an extra dimension to the current tag taxonomy. By referencing previous studies and learning from industrial perspectives, we create a refined taxonomy for the intentions of technical forum posts. Through manual labeling and analysis on a sampled post dataset extracted from online forums, we understand the relevance between the constitution of posts (code, error messages) and their intentions. Furthermore, inspired by our manual study, we design a pre-trained transformer-based model to automatically predict post intentions. The best variant of our intention prediction framework, which achieves a Micro F1-score of 0.589, Top 1-3 accuracy of 62.6% to 87.8%, and an average AUC of 0.787, outperforms the state-of-the-art baseline approach. Our characterization and automated classification of forum posts regarding their intentions may help forum maintainers or third-party tool developers improve the organization and retrieval of posts on technical forums. We have released our annotated dataset and codes in our supplementary material package.
Authors: Kellin Pelrine, Mohammad Taufeeque, Michał Zając, Euan McLean, Adam Gleave
Language model attacks typically assume one of two extreme threat models: full white-box access to model weights, or black-box access limited to a text generation API. However, real-world APIs are often more flexible than just text generation: these APIs expose ``gray-box'' access leading to new threat vectors. To explore this, we red-team three new functionalities exposed in the GPT-4 APIs: fine-tuning, function calling and knowledge retrieval. We find that fine-tuning a model on as few as 15 harmful examples or 100 benign examples can remove core safeguards from GPT-4, enabling a range of harmful outputs. Furthermore, we find that GPT-4 Assistants readily divulge the function call schema and can be made to execute arbitrary function calls. Finally, we find that knowledge retrieval can be hijacked by injecting instructions into retrieval documents. These vulnerabilities highlight that any additions to the functionality exposed by an API can create new vulnerabilities.
Authors: Katrin Tomanek, Shanqing Cai, Subhashini Venugopalan
Abbreviation expansion is a strategy used to speed up communication by limiting the amount of typing and using a language model to suggest expansions. Here we look at personalizing a Large Language Model's (LLM) suggestions based on prior conversations to enhance the relevance of predictions, particularly when the user data is small (~1000 samples). Specifically, we compare fine-tuning, prompt-tuning, and retrieval augmented generation of expanded text suggestions for abbreviated inputs. Our case study with a deployed 8B parameter LLM on a real user living with ALS, and experiments on movie character personalization indicates that (1) customization may be necessary in some scenarios and prompt-tuning generalizes well to those, (2) fine-tuning on in-domain data (with as few as 600 samples) still shows some gains, however (3) retrieval augmented few-shot selection also outperforms fine-tuning. (4) Parameter efficient tuning allows for efficient and scalable personalization. For prompt-tuning, we also find that initializing the learned "soft-prompts" to user relevant concept tokens leads to higher accuracy than random initialization.
Authors: Zhichao Xu
Query-focused summarization (QFS) aims to provide a summary of a single document/multi documents that can satisfy the information needs of a given query. It is useful for various real-world applications, such as abstractive snippet generation or more recent retrieval augmented generation (RAG). A prototypical QFS pipeline consists of a retriever (sparse or dense retrieval) and a generator (usually a large language model). However, applying large language models (LLM) potentially leads to hallucinations, especially when the evidence contradicts the prior belief of LLMs. There has been growing interest in developing new decoding methods to improve generation quality and reduce hallucination. In this work, we conduct a large-scale reproducibility on one recently proposed decoding method -- Context-aware Decoding (CAD). In addition to replicating CAD's experiments on news summarization datasets, we include experiments on QFS datasets, and conduct more rigorous analysis on computational complexity and hyperparameter sensitivity. Experiments with eight different language models show that performance-wise, CAD improves QFS quality by (1) reducing factuality errors/hallucinations while (2) mostly retaining the match of lexical patterns, measured by ROUGE scores, while also at a cost of increased inference-time FLOPs and reduced decoding speed. The code implementation based on Huggingface Library is made available https://github.com/zhichaoxu-shufe/context-aware-decoding-qfs
Authors: Behnam Rahdari, Hao Ding, Ziwei Fan, Yifei Ma, Zhuotong Chen, Anoop Deoras, Branislav Kveton
The unique capabilities of Large Language Models (LLMs), such as the natural language text generation ability, position them as strong candidates for providing explanation for recommendations. However, despite the size of the LLM, most existing models struggle to produce zero-shot explanations reliably. To address this issue, we propose a framework called Logic-Scaffolding, that combines the ideas of aspect-based explanation and chain-of-thought prompting to generate explanations through intermediate reasoning steps. In this paper, we share our experience in building the framework and present an interactive demonstration for exploring our results.
Authors: Priyesh Vakharia, Devavrat Joshi, Meenal Chavan, Dhananjay Sonawane, Bhrigu Garg, Parsa Mazaheri, Ian Lane
Large Language Models (LLMs) are adept at text manipulation -- tasks such as machine translation and text summarization. However, these models can also be prone to hallucination, which can be detrimental to the faithfulness of any answers that the model provides. Recent works in combating hallucinations in LLMs deal with identifying hallucinated sentences and categorizing the different ways in which models hallucinate. This paper takes a deep dive into LLM behavior with respect to hallucinations, defines a token-level approach to identifying different kinds of hallucinations, and further utilizes this token-level tagging to improve the interpretability and faithfulness of LLMs in dialogue summarization tasks. Through this, the paper presents a new, enhanced dataset and a new training paradigm.
Authors: Samaksh Gulati, Anshit Verma, Manoj Parmar, Palash Chaudhary
Large "instruction-tuned" language models (i.e., finetuned to respond to instructions) have demonstrated a remarkable ability to generalize zero-shot to new tasks. Nevertheless, they depend heavily on human-written instruction data that is often limited in quantity, diversity, and creativity, therefore hindering the generality of the tuned model. We conducted a quantitative study to figure out the efficacy of machine-generated annotations, where we compare the results of a fine-tuned BERT model with human v/s machine-generated annotations. Applying our methods to the vanilla GPT-3 model, we saw that machine generated annotations were 78.54% correct and the fine-tuned model achieved a 96.01% model performance compared to the performance with human-labelled annotations. This result shows that machine-generated annotations are a resource and cost effective way to fine-tune down-stream models.
Authors: Hongyin Zhu
Large language models (LLMs) are increasingly being used in Metaverse environments to generate dynamic and realistic content and to control the behavior of non-player characters (NPCs). However, the cybersecurity concerns associated with LLMs have become increasingly prominent. Previous research has primarily focused on patching system vulnerabilities to enhance cybersecurity, but these approaches are not well-suited to the Metaverse, where the virtual space is more complex, LLMs are vulnerable, and ethical user interaction is critical. Moreover, the scope of cybersecurity in the Metaverse is expected to expand significantly. This paper proposes a method for enhancing cybersecurity through the simulation of user interaction with LLMs. Our goal is to educate users and strengthen their defense capabilities through exposure to a comprehensive simulation system. This system includes extensive Metaverse cybersecurity Q&A and attack simulation scenarios. By engaging with these, users will improve their ability to recognize and withstand risks. Additionally, to address the ethical implications of user input, we propose using LLMs as evaluators to assess user content across five dimensions. We further adapt the models through vocabulary expansion training to better understand personalized inputs and emoticons. We conduct experiments on multiple LLMs and find that our approach is effective.
Authors: Aoxiong Yin, Tianyun Zhong, Haoyuan Li, Siliang Tang, Zhou Zhao
The primary objective of simultaneous machine translation (SiMT) is to minimize latency while preserving the quality of the final translation. Drawing inspiration from CPU branch prediction techniques, we propose incorporating branch prediction techniques in SiMT tasks to reduce translation latency. Specifically, we utilize a language model as a branch predictor to predict potential branch directions, namely, future source words. Subsequently, we utilize the predicted source words to decode the output in advance. When the actual source word deviates from the predicted source word, we use the real source word to decode the output again, replacing the predicted output. To further reduce computational costs, we share the parameters of the encoder and the branch predictor, and utilize a pre-trained language model for initialization. Our proposed method can be seamlessly integrated with any SiMT model. Extensive experimental results demonstrate that our approach can improve translation quality and latency at the same time. Our code is available at https://github.com/YinAoXiong/simt_branch_predictor .
Authors: Hisaichi Shibata
Equivariance is an important feature in machine learning, including language models. It ensures that any sequences of phrases with the same meanings are interpreted consistently. For example, the sentence 'There is a cat on the table' should be interpreted by language models as it is, regardless of variations in its token-level expression. Building on this insight, I propose a new theory suggesting that insufficient equivariance in language models can lead to hallucinations. According to this theory, which is both intuitive and novel, language models trained on relatively small datasets tend to misinterpret input texts and/or generate incorrect texts (i.e., hallucinations). To test this theory, I developed a toy model known as 'dancing men', which is a character-level substitution cipher. Additionally, I propose a novel technique based on the T5 (Text To Text Transfer Transformer) model to efficiently decipher these codes without relying on frequency analysis. I have found that this T5 model can almost completely solve the cipher, demonstrating its ability to acquire equivariance in this frame. This method could be scaled up to word-level and sentence-level substitution ciphers, analogous to large language models without tokenizers or dictionaries. This scalability makes it suitable for investigating the proposed link between inadequate equivariance acquisition and the emergence of hallucinations.
Authors: Nikhilesh Bhatnagar, Ashok Urlana, Vandan Mujadia, Pruthwik Mishra, Dipti Misra Sharma
Cross-lingual summarization involves the summarization of text written in one language to a different one. There is a body of research addressing cross-lingual summarization from English to other European languages. In this work, we aim to perform cross-lingual summarization from English to Hindi. We propose pairing up the coverage of newsworthy events in textual and video format can prove to be helpful for data acquisition for cross lingual summarization. We analyze the data and propose methods to match articles to video descriptions that serve as document and summary pairs. We also outline filtering methods over reasonable thresholds to ensure the correctness of the summaries. Further, we make available 28,583 mono and cross-lingual article-summary pairs https://github.com/tingc9/Cross-Sum-News-Aligned. We also build and analyze multiple baselines on the collected data and report error analysis.
Authors: Rongsheng Wang, Haoming Chen, Ruizhe Zhou, Yaofei Duan, Kunyan Cai, Han Ma, Jiaxi Cui, Jian Li, Patrick Cheong-Iao Pang, Yapeng Wang, Tao Tan
Existing research has demonstrated that refining large language models (LLMs) through the utilization of machine-generated instruction-following data empowers these models to exhibit impressive zero-shot capabilities for novel tasks, without requiring human-authored instructions. In this paper, we systematically investigate, preprocess, and integrate three Chinese instruction-following datasets with the aim of enhancing the Chinese conversational capabilities of Mixtral-8x7B sparse Mixture-of-Experts model. Through instruction fine-tuning on this carefully processed dataset, we successfully construct the Mixtral-8x7B sparse Mixture-of-Experts model named "Aurora." To assess the performance of Aurora, we utilize three widely recognized benchmark tests: C-Eval, MMLU, and CMMLU. Empirical studies validate the effectiveness of instruction fine-tuning applied to Mixtral-8x7B sparse Mixture-of-Experts model. This work is pioneering in the execution of instruction fine-tuning on a sparse expert-mixed model, marking a significant breakthrough in enhancing the capabilities of this model architecture. Our code, data and model are publicly available at: https://github.com/WangRongsheng/Aurora
Authors: Zhenlin Su, Liyan Xu, Jin Xu, Jiangnan Li, Mingdu Huangfu
Identifying speakers of quotations in narratives is an important task in literary analysis, with challenging scenarios including the out-of-domain inference for unseen speakers, and non-explicit cases where there are no speaker mentions in surrounding context. In this work, we propose a simple and effective approach SIG, a generation-based method that verbalizes the task and quotation input based on designed prompt templates, which also enables easy integration of other auxiliary tasks that further bolster the speaker identification performance. The prediction can either come from direct generation by the model, or be determined by the highest generation probability of each speaker candidate. Based on our approach design, SIG supports out-of-domain evaluation, and achieves open-world classification paradigm that is able to accept any forms of candidate input. We perform both cross-domain evaluation and in-domain evaluation on PDNC, the largest dataset of this task, where empirical results suggest that SIG outperforms previous baselines of complicated designs, as well as the zero-shot ChatGPT, especially excelling at those hard non-explicit scenarios by up to 17% improvement. Additional experiments on another dataset WP further corroborate the efficacy of SIG.
Authors: Weiwen Xu, Deng Cai, Zhisong Zhang, Wai Lam, Shuming Shi
As humans, we consistently engage in interactions with our peers and receive feedback in the form of natural language. This language feedback allows us to reflect on our actions, maintain appropriate behavior, and rectify our errors. The question arises naturally: can we use language feedback to align large language models (LLMs)? In contrast to previous research that aligns LLMs with reward or preference data, we present the first systematic exploration of alignment through the lens of language feedback (i.e., judgment). We commence with an in-depth investigation of potential methods that can be adapted for aligning LLMs with judgments, revealing that these methods are unable to fully capitalize on the judgments. To facilitate more effective utilization of judgments, we propose a novel framework, Contrastive Unlikelihood Training (CUT), that allows for fine-grained inappropriate content detection and correction based on judgments. Our offline alignment results show that, with merely 1317 off-the-shelf judgment data, CUT (LLaMA2-13b) can beat the 175B DaVinci003 and surpass the best baseline by 52.34 points on AlpacaEval. The online alignment results demonstrate that CUT can align LLMs (LLaMA2-chat-13b) in an iterative fashion using model-specific judgment data, with a steady performance improvement from 81.09 to 91.36 points on AlpacaEval. Our analysis further suggests that judgments exhibit greater potential than rewards for LLM alignment and warrant future research.
Authors: Atsunori Ogawa, Naohiro Tawara, Takatomo Kano, Marc Delcroix
Confidence estimation, in which we estimate the reliability of each recognized token (e.g., word, sub-word, and character) in automatic speech recognition (ASR) hypotheses and detect incorrectly recognized tokens, is an important function for developing ASR applications. In this study, we perform confidence estimation for end-to-end (E2E) ASR hypotheses. Recent E2E ASR systems show high performance (e.g., around 5% token error rates) for various ASR tasks. In such situations, confidence estimation becomes difficult since we need to detect infrequent incorrect tokens from mostly correct token sequences. To tackle this imbalanced dataset problem, we employ a bidirectional long short-term memory (BLSTM)-based model as a strong binary-class (correct/incorrect) sequence labeler that is trained with a class balancing objective. We experimentally confirmed that, by utilizing several types of ASR decoding scores as its auxiliary features, the model steadily shows high confidence estimation performance under highly imbalanced settings. We also confirmed that the BLSTM-based model outperforms Transformer-based confidence estimation models, which greatly underestimate incorrect tokens.
Authors: Hongda Sun, Hongzhan Lin, Rui Yan
Electronic health records (EHRs) have become the foundation of machine learning applications in healthcare, while the utility of real patient records is often limited by privacy and security concerns. Synthetic EHR generation provides an additional perspective to compensate for this limitation. Most existing methods synthesize new records based on real EHR data, without consideration of different types of events in EHR data, which cannot control the event combinations in line with medical common sense. In this paper, we propose MSIC, a Multi-visit health Status Inference model for Collaborative EHR synthesis to address these limitations. First, we formulate the synthetic EHR generation process as a probabilistic graphical model and tightly connect different types of events by modeling the latent health states. Then, we derive a health state inference method tailored for the multi-visit scenario to effectively utilize previous records to synthesize current and future records. Furthermore, we propose to generate medical reports to add textual descriptions for each medical event, providing broader applications for synthesized EHR data. For generating different paragraphs in each visit, we incorporate a multi-generator deliberation framework to collaborate the message passing of multiple generators and employ a two-phase decoding strategy to generate high-quality reports. Our extensive experiments on the widely used benchmarks, MIMIC-III and MIMIC-IV, demonstrate that MSIC advances state-of-the-art results on the quality of synthetic data while maintaining low privacy risks.
Authors: Sourabrata Mukherjee, Zdeněk Kasner, Ondřej Dušek
Text sentiment transfer aims to flip the sentiment polarity of a sentence (positive to negative or vice versa) while preserving its sentiment-independent content. Although current models show good results at changing the sentiment, content preservation in transferred sentences is insufficient. In this paper, we present a sentiment transfer model based on polarity-aware denoising, which accurately controls the sentiment attributes in generated text, preserving the content to a great extent and helping to balance the style-content trade-off. Our proposed model is structured around two key stages in the sentiment transfer process: better representation learning using a shared encoder and sentiment-controlled generation using separate sentiment-specific decoders. Empirical results show that our methods outperforms state-of-the-art baselines in terms of content preservation while staying competitive in terms of style transfer accuracy and fluency.
Authors: Hayate Funakura, Koji Mineshima
We present a compositional semantics for various types of polar questions and wh-questions within the framework of Combinatory Categorial Grammar (CCG). To assess the explanatory power of our proposed analysis, we introduce a question-answering dataset QSEM specifically designed to evaluate the semantics of interrogative sentences. We implement our analysis using existing CCG parsers and conduct evaluations using the dataset. Through the evaluation, we have obtained annotated data with CCG trees and semantic representations for about half of the samples included in QSEM. Furthermore, we discuss the discrepancy between the theoretical capacity of CCG and the capabilities of existing CCG parsers.
Authors: Abiodun Finbarrs Oketunji, Muhammad Anas, Deepthi Saina
The Large Language Model Bias Index (LLMBI) is a pioneering approach designed to quantify and address biases inherent in large language models (LLMs), such as GPT-4. We recognise the increasing prevalence and impact of LLMs across diverse sectors. This research introduces a novel metric, LLMBI, to systematically measure and mitigate biases potentially skewing model responses. We formulated LLMBI using a composite scoring system incorporating multiple dimensions of bias, including but not limited to age, gender, and racial biases.
To operationalise this metric, we engaged in a multi-step process involving collecting and annotating LLM responses, applying sophisticated Natural Language Processing (NLP) techniques for bias detection, and computing the LLMBI score through a specially crafted mathematical formula. The formula integrates weighted averages of various bias dimensions, a penalty for dataset diversity deficiencies, and a correction for sentiment biases. Our empirical analysis, conducted using responses from OpenAI's API, employs advanced sentiment analysis as a representative method for bias detection.
The research reveals LLMs, whilst demonstrating impressive capabilities in text generation, exhibit varying degrees of bias across different dimensions. LLMBI provides a quantifiable measure to compare biases across models and over time, offering a vital tool for systems engineers, researchers and regulators in enhancing the fairness and reliability of LLMs. It highlights the potential of LLMs in mimicking unbiased human-like responses. Additionally, it underscores the necessity of continuously monitoring and recalibrating such models to align with evolving societal norms and ethical standards.
Authors: Ben Eyal, Amir Bachar, Ophir Haroche, Michael Elhadad
Large Language Models (LLMs) have spurred progress in text-to-SQL, the task of generating SQL queries from natural language questions based on a given database schema. Despite the declarative nature of SQL, it continues to be a complex programming language. In this paper, we investigate the potential of an alternative query language with simpler syntax and modular specification of complex queries. The purpose is to create a query language that can be learned more easily by modern neural semantic parsing architectures while also enabling non-programmers to better assess the validity of the query plans produced by an interactive query plan assistant.
The proposed alternative query language is called Query Plan Language (QPL). It is designed to be modular and can be translated into a restricted form of SQL Common Table Expressions (CTEs). The aim of QPL is to make complex data retrieval accessible to non-programmers by allowing users to express their questions in natural language while also providing an easier-to-verify target language. The paper demonstrates how neural LLMs can benefit from QPL's modularity to generate complex query plans in a compositional manner. This involves a question decomposition strategy and a planning stage.
We conduct experiments on a version of the Spider text-to-SQL dataset that has been converted to QPL. The hierarchical structure of QPL programs enables us to measure query complexity naturally. Based on this assessment, we identify the low accuracy of existing text-to-SQL systems on complex compositional queries. We present ways to address the challenge of complex queries in an iterative, user-controlled manner, using fine-tuned LLMs and a variety of prompting strategies in a compositional manner.
Authors: Lois Wong
Providing mental healthcare to individuals with limited English proficiency (LEP) remains a pressing problem within psychiatry. Because the majority of individuals trained in providing psychiatric care are English speakers, the quality of mental healthcare given to LEP patients is significantly lower than that provided for English speakers. The provision of mental healthcare is contingent on communication and understanding between the patient and healthcare provider, much more so than in the realm of physical healthcare, and English speakers are often unable to comprehend figurative language such as metaphors used by LEPs. Hence, Figurative Language Translation is invaluable to providing equitable psychiatric care. Now, metaphor has been shown to be paramount in both identifying individuals struggling with mental problems and helping those individuals understand and communicate their experiences. Therefore, this paper aims to survey the potential of Machine Translation for providing equitable psychiatric healthcare and highlights the need for further research on the transferability of existing machine and metaphor translation research in the domain of psychiatry.
Authors: Yin Luo, Qingchao Kong, Nan Xu, Jia Cao, Bao Hao, Baoyu Qu, Bo Chen, Chao Zhu, Chenyang Zhao, Donglei Zhang, Fan Feng, Feifei Zhao, Hailong Sun, Hanxuan Yang, Haojun Pan, Hongyu Liu, Jianbin Guo, Jiangtao Du, Jingyi Wang, Junfeng Li, Lei Sun, Liduo Liu, Lifeng Dong, Lili Liu, Lin Wang, Liwen Zhang, Minzheng Wang, Pin Wang, Ping Yu, Qingxiao Li, Rui Yan, Rui Zou, Ruiqun Li, Taiwen Huang, Xiaodong Wang, Xiaofei Wu, Xin Peng, Xina Zhang, Xing Fang, Xinglin Xiao, Yanni Hao, Yao Dong, Yigang Wang, Ying Liu, Yongyu Jiang, Yungan Wang, Yuqi Wang, Zhangsheng Wang, Zhaoxin Yu, Zhen Luo, Wenji Mao, Lei Wang, Dajun Zeng
As the latest advancements in natural language processing, large language models (LLMs) have achieved human-level language understanding and generation abilities in many real-world tasks, and even have been regarded as a potential path to the artificial general intelligence. To better facilitate research on LLMs, many open-source LLMs, such as Llama 2 and Falcon, have recently been proposed and gained comparable performances to proprietary models. However, these models are primarily designed for English scenarios and exhibit poor performances in Chinese contexts. In this technical report, we propose YAYI 2, including both base and chat models, with 30 billion parameters. YAYI 2 is pre-trained from scratch on a multilingual corpus which contains 2.65 trillion tokens filtered by our pre-training data processing pipeline. The base model is aligned with human values through supervised fine-tuning with millions of instructions and reinforcement learning from human feedback. Extensive experiments on multiple benchmarks, such as MMLU and CMMLU, consistently demonstrate that the proposed YAYI 2 outperforms other similar sized open-source models.
Authors: Max Ku, Dongfu Jiang, Cong Wei, Xiang Yue, Wenhu Chen
In the rapidly advancing field of conditional image generation research, challenges such as limited explainability lie in effectively evaluating the performance and capabilities of various models. This paper introduces VIESCORE, a Visual Instruction-guided Explainable metric for evaluating any conditional image generation tasks. VIESCORE leverages general knowledge from Multimodal Large Language Models (MLLMs) as the backbone and does not require training or fine-tuning. We evaluate VIESCORE on seven prominent tasks in conditional image tasks and found: (1) VIESCORE (GPT4-v) achieves a high Spearman correlation of 0.3 with human evaluations, while the human-to-human correlation is 0.45. (2) VIESCORE (with open-source MLLM) is significantly weaker than GPT-4v in evaluating synthetic images. (3) VIESCORE achieves a correlation on par with human ratings in the generation tasks but struggles in editing tasks. With these results, we believe VIESCORE shows its great potential to replace human judges in evaluating image synthesis tasks.
Authors: Abhinav Arun, Ashish Dhiman, Mehul Soni, Yibei Hu
Financial reports offer critical insights into a company's operations, yet their extensive length typically spanning 30 40 pages poses challenges for swift decision making in dynamic markets. To address this, we leveraged finetuned Large Language Models (LLMs) to distill key indicators and operational metrics from these reports basis questions from the user. We devised a method to locate critical data, and leverage the FinQA dataset to fine-tune both Llama-2 7B and T5 models for customized question answering. We achieved results comparable to baseline on the final numerical answer, a competitive accuracy in numerical reasoning and calculation.
Authors: Nico Potyka, Yuqicheng Zhu, Yunjie He, Evgeny Kharlamov, Steffen Staab
Large-language models (LLMs) have the potential to support a wide range of applications like conversational agents, creative writing, text improvement, and general query answering. However, they are ill-suited for query answering in high-stake domains like medicine because they generate answers at random and their answers are typically not robust - even the same query can result in different answers when prompted multiple times. In order to improve the robustness of LLM queries, we propose using ranking queries repeatedly and to aggregate the queries using methods from social choice theory. We study ranking queries in diagnostic settings like medical and fault diagnosis and discuss how the Partial Borda Choice function from the literature can be applied to merge multiple query results. We discuss some additional interesting properties in our setting and evaluate the robustness of our approach empirically.
Authors: Lizhou Fan, Wenyue Hua, Lingyao Li, Haoyang Ling, Yongfeng Zhang, Libby Hemphill
Complex reasoning ability is one of the most important features of current LLMs, which has also been leveraged to play an integral role in complex decision-making tasks. Therefore, the investigation into the reasoning capabilities of Large Language Models (LLMs) is critical: numerous benchmarks have been established to assess the reasoning abilities of LLMs. However, current benchmarks are inadequate in offering a rigorous evaluation of the full extent of reasoning abilities that LLMs are capable of achieving. They are also prone to the risk of overfitting, as these benchmarks, being publicly accessible and static, allow models to potentially tailor their responses to specific benchmark metrics, thereby inflating their performance. Addressing these limitations, our research introduces a new benchmark, named NPHardEval. This benchmark is designed to evaluate the reasoning abilities of LLMs across a broad spectrum of 900 algorithmic questions, extending up to the NP-Hard complexity class. These questions are meticulously chosen to represent a wide range of complexity class below the NP-hard complexity class, offering a rigorous measure of the reasoning ability of LLMs. Through this study, we shed light on the current state of reasoning in LLMs, providing an objective and rigorous perspective through the comparison of LLMs' performance across complex classes. Moreover, this benchmark is designed with a dynamic update mechanism, where the datapoints are refreshed on a monthly basis. Such regular updates play a crucial role in mitigating the risk of LLMs overfitting to the benchmark, promoting a more accurate and reliable assessment of their reasoning capabilities. The benchmark dataset and code of NPHardEval are available at https://github.com/casmlab/NPHardEval.
Authors: Stefano Lusito, Edoardo Ferrante, Jean Maillard
Text normalization is a crucial technology for low-resource languages which lack rigid spelling conventions or that have undergone multiple spelling reforms. Low-resource text normalization has so far relied upon hand-crafted rules, which are perceived to be more data efficient than neural methods. In this paper we examine the case of text normalization for Ligurian, an endangered Romance language. We collect 4,394 Ligurian sentences paired with their normalized versions, as well as the first open source monolingual corpus for Ligurian. We show that, in spite of the small amounts of data available, a compact transformer-based model can be trained to achieve very low error rates by the use of backtranslation and appropriate tokenization.
Authors: Nathaniel Weir, Peter Clark, Benjamin Van Durme
Our goal is a modern approach to answering questions via systematic reasoning where answers are supported by human interpretable proof trees grounded in an NL corpus of authoritative facts. Such a system would help alleviate the challenges of interpretability and hallucination with modern LMs, and the lack of grounding of current explanation methods (e.g., Chain-of-Thought). This paper proposes a new take on Prolog-based inference engines, where we replace handcrafted rules with a combination of neural language modeling, guided generation, and semiparametric dense retrieval. Our implementation, NELLIE, is the first system to demonstrate fully interpretable, end-to-end grounded QA as entailment tree proof search, going beyond earlier work explaining known-to-be-true facts from text. In experiments, NELLIE outperforms a similar-sized state-of-the-art reasoner [Tafjord et al., 2022] while producing knowledge-grounded explanations. We also find NELLIE can exploit both semi-structured and NL text corpora to guide reasoning. Together these suggest a new way to jointly reap the benefits of both modern neural methods and traditional symbolic reasoning.
Authors: Guoqing Luo, Yu Tong Han, Lili Mou, Mauajama Firdaus
Prompting approaches have been recently explored in text style transfer, where a textual prompt is used to query a pretrained language model to generate style-transferred texts word by word in an autoregressive manner. However, such a generation process is less controllable and early prediction errors may affect future word predictions. In this paper, we present a prompt-based editing approach for text style transfer. Specifically, we prompt a pretrained language model for style classification and use the classification probability to compute a style score. Then, we perform discrete search with word-level editing to maximize a comprehensive scoring function for the style-transfer task. In this way, we transform a prompt-based generation problem into a classification one, which is a training-free process and more controllable than the autoregressive generation of sentences. In our experiments, we performed both automatic and human evaluation on three style-transfer benchmark datasets, and show that our approach largely outperforms the state-of-the-art systems that have 20 times more parameters. Additional empirical analyses further demonstrate the effectiveness of our approach.
Authors: Mingyang Song, Haiyun Jiang, Shuming Shi, Songfang Yao, Shilong Lu, Yi Feng, Huafeng Liu, Liping Jing
The emergence of ChatGPT has recently garnered significant attention from the computational linguistics community. To demonstrate its capabilities as a keyphrase generator, we conduct a preliminary evaluation of ChatGPT for the keyphrase generation task. We evaluate its performance in various aspects, including keyphrase generation prompts, keyphrase generation diversity, and long document understanding. Our evaluation is based on six benchmark datasets, and we adopt the prompt suggested by OpenAI while extending it to six candidate prompts. We find that ChatGPT performs exceptionally well on all six candidate prompts, with minor performance differences observed across the datasets. Based on our findings, we conclude that ChatGPT has great potential for keyphrase generation. Moreover, we discover that ChatGPT still faces challenges when it comes to generating absent keyphrases. Meanwhile, in the final section, we also present some limitations and future expansions of this report.
Authors: Afra Amini, Massimiliano Ciaramita
Large language models are able to learn new tasks in context, where they are provided with instructions and a few annotated examples. However, the effectiveness of in-context learning is dependent on the provided context, and the performance on a downstream task can vary considerably, depending on the instruction. Importantly, such dependency on the context can surface in unpredictable ways, e.g., a seemingly more informative instruction might lead to a worse performance. In this paper, we propose an alternative approach, which we term In-Context Probing (ICP). Similar to in-context learning, we contextualize the representation of the input with an instruction, but instead of decoding the output prediction, we probe the contextualized representation to predict the label. Through a series of experiments on a diverse set of classification tasks, we show that in-context probing is significantly more robust to changes in instructions. We further show that ICP performs competitive or superior to finetuning and can be particularly helpful to build classifiers on top of smaller models, with less than a hundred training examples.
Authors: Yufei Tian, Anjali Narayan-Chen, Shereen Oraby, Alessandra Cervone, Gunnar Sigurdsson, Chenyang Tao, Wenbo Zhao, Yiwen Chen, Tagyoung Chung, Jing Huang, Nanyun Peng
Automatic melody-to-lyric generation is a task in which song lyrics are generated to go with a given melody. It is of significant practical interest and more challenging than unconstrained lyric generation as the music imposes additional constraints onto the lyrics. The training data is limited as most songs are copyrighted, resulting in models that underfit the complicated cross-modal relationship between melody and lyrics. In this work, we propose a method for generating high-quality lyrics without training on any aligned melody-lyric data. Specifically, we design a hierarchical lyric generation framework that first generates a song outline and second the complete lyrics. The framework enables disentanglement of training (based purely on text) from inference (melody-guided text generation) to circumvent the shortage of parallel data.
We leverage the segmentation and rhythm alignment between melody and lyrics to compile the given melody into decoding constraints as guidance during inference. The two-step hierarchical design also enables content control via the lyric outline, a much-desired feature for democratizing collaborative song creation. Experimental results show that our model can generate high-quality lyrics that are more on-topic, singable, intelligible, and coherent than strong baselines, for example SongMASS, a SOTA model trained on a parallel dataset, with a 24% relative overall quality improvement based on human ratings.
Authors: Xiang 'Anthony' Chen, Jeff Burke, Ruofei Du, Matthew K. Hong, Jennifer Jacobs, Philippe Laban, Dingzeyu Li, Nanyun Peng, Karl D. D. Willis, Chien-Sheng Wu, Bolei Zhou
Through iterative, cross-disciplinary discussions, we define and propose next-steps for Human-centered Generative AI (HGAI). We contribute a comprehensive research agenda that lays out future directions of Generative AI spanning three levels: aligning with human values; assimilating human intents; and augmenting human abilities. By identifying these next-steps, we intend to draw interdisciplinary research teams to pursue a coherent set of emergent ideas in HGAI, focusing on their interested topics while maintaining a coherent big picture of the future work landscape.
Authors: Xinyi Wang, Lucas Caccia, Oleksiy Ostapenko, Xingdi Yuan, Alessandro Sordoni
Large language models (LLMs) have recently attracted considerable interest for their ability to perform complex reasoning tasks, such as chain-of-thought reasoning. However, most of the existing approaches to enhance this ability rely heavily on data-driven methods, while neglecting the structural aspects of the model's reasoning capacity. We find that while LLMs can manage individual reasoning steps well, they struggle with maintaining consistency across an entire reasoning chain. To solve this, we introduce 'planning tokens' at the start of each reasoning step, serving as a guide for the model. These token embeddings are then fine-tuned along with the rest of the model parameters. Our approach requires a negligible increase in trainable parameters (just 0.001%) and can be applied through either full fine-tuning or a more parameter-efficient scheme. We demonstrate our method's effectiveness by applying it to three different LLMs, showing notable accuracy improvements across three math word problem datasets w.r.t. plain chain-of-thought fine-tuning baselines.
Authors: Jiashuo Wang, Haozhao Wang, Shichao Sun, Wenjie Li
In the quest to advance human-centric natural language generation (NLG) systems, ensuring alignment between NLG models and human preferences is crucial. For this alignment, current popular methods leverage a reinforcement learning (RL) approach with a reward model trained on feedback from humans. However, inherent disagreements due to the subjective nature of human preferences pose a significant challenge for training the reward model, resulting in a deterioration of the NLG performance. To tackle this issue, previous approaches typically rely on majority voting or averaging to consolidate multiple inconsistent preferences into a merged one. Although straightforward to understand and execute, such methods suffer from an inability to capture the nuanced degrees of disaggregation among humans and may only represent a specialized subset of individuals, thereby lacking the ability to quantitatively disclose the universality of human preferences. To address this challenge, this paper proposes a novel approach, which employs a Bayesian framework to account for the distribution of disagreements among human preferences as training a preference model, and names it as d-PM. Besides, considering the RL strategy's inefficient and complex training process over the training efficiency, we further propose utilizing the contrastive learning strategy to train the NLG model with the preference scores derived from the d-PM model. Extensive experiments on two human-centric NLG tasks, i.e., emotional support conversation and integrity "Rule-of-Thumb" generation, show that our method consistently exceeds previous SOTA models in both automatic and human evaluations.
Authors: Ningyu Xu, Qi Zhang, Jingting Ye, Menghan Zhang, Xuanjing Huang
Large language models (LLMs) have exhibited considerable cross-lingual generalization abilities, whereby they implicitly transfer knowledge across languages. However, the transfer is not equally successful for all languages, especially for low-resource ones, which poses an ongoing challenge. It is unclear whether we have reached the limits of implicit cross-lingual generalization and if explicit knowledge transfer is viable. In this paper, we investigate the potential for explicitly aligning conceptual correspondence between languages to enhance cross-lingual generalization. Using the syntactic aspect of language as a testbed, our analyses of 43 languages reveal a high degree of alignability among the spaces of structural concepts within each language for both encoder-only and decoder-only LLMs. We then propose a meta-learning-based method to learn to align conceptual spaces of different languages, which facilitates zero-shot and few-shot generalization in concept classification and also offers insights into the cross-lingual in-context learning phenomenon. Experiments on syntactic analysis tasks show that our approach achieves competitive results with state-of-the-art methods and narrows the performance gap between languages, particularly benefiting those with limited resources.
Authors: Zeyu Gao, Hao Wang, Yuchen Zhou, Wenyu Zhu, Chao Zhang
As software becomes increasingly complex and prone to vulnerabilities, automated vulnerability detection is critically important, yet challenging. Given the significant successes of large language models (LLMs) in various tasks, there is growing anticipation of their efficacy in vulnerability detection. However, a quantitative understanding of their potential in vulnerability detection is still missing. To bridge this gap, we introduce a comprehensive vulnerability benchmark VulBench. This benchmark aggregates high-quality data from a wide range of CTF (Capture-the-Flag) challenges and real-world applications, with annotations for each vulnerable function detailing the vulnerability type and its root cause. Through our experiments encompassing 16 LLMs and 6 state-of-the-art (SOTA) deep learning-based models and static analyzers, we find that several LLMs outperform traditional deep learning approaches in vulnerability detection, revealing an untapped potential in LLMs. This work contributes to the understanding and utilization of LLMs for enhanced software security.
Authors: Xiang Yue, Yuansheng Ni, Kai Zhang, Tianyu Zheng, Ruoqi Liu, Ge Zhang, Samuel Stevens, Dongfu Jiang, Weiming Ren, Yuxuan Sun, Cong Wei, Botao Yu, Ruibin Yuan, Renliang Sun, Ming Yin, Boyuan Zheng, Zhenzhu Yang, Yibo Liu, Wenhao Huang, Huan Sun, Yu Su, Wenhu Chen
We introduce MMMU: a new benchmark designed to evaluate multimodal models on massive multi-discipline tasks demanding college-level subject knowledge and deliberate reasoning. MMMU includes 11.5K meticulously collected multimodal questions from college exams, quizzes, and textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering. These questions span 30 subjects and 183 subfields, comprising 30 highly heterogeneous image types, such as charts, diagrams, maps, tables, music sheets, and chemical structures. Unlike existing benchmarks, MMMU focuses on advanced perception and reasoning with domain-specific knowledge, challenging models to perform tasks akin to those faced by experts. The evaluation of 14 open-source LMMs as well as the proprietary GPT-4V(ision) and Gemini highlights the substantial challenges posed by MMMU. Even the advanced GPT-4V and Gemini Ultra only achieve accuracies of 56% and 59% respectively, indicating significant room for improvement. We believe MMMU will stimulate the community to build next-generation multimodal foundation models towards expert artificial general intelligence.
Authors: Shuyang Sun, Runjia Li, Philip Torr, Xiuye Gu, Siyang Li
Existing open-vocabulary image segmentation methods require a fine-tuning step on mask annotations and/or image-text datasets. Mask labels are labor-intensive, which limits the number of categories in segmentation datasets. As a result, the open-vocabulary capacity of pre-trained VLMs is severely reduced after fine-tuning. However, without fine-tuning, VLMs trained under weak image-text supervision tend to make suboptimal mask predictions when there are text queries referring to non-existing concepts in the image. To alleviate these issues, we introduce a novel recurrent framework that progressively filters out irrelevant texts and enhances mask quality without training efforts. The recurrent unit is a two-stage segmenter built upon a VLM with frozen weights. Thus, our model retains the VLM's broad vocabulary space and strengthens its segmentation capability. Experimental results show that our method outperforms not only the training-free counterparts, but also those fine-tuned with millions of additional data samples, and sets new state-of-the-art records for both zero-shot semantic and referring image segmentation tasks. Specifically, we improve the current record by 28.8, 16.0, and 6.9 mIoU on Pascal VOC, COCO Object, and Pascal Context.
Authors: Katsumasa Yoshikawa, Takato Yamazaki, Masaya Ohagi, Tomoya Mizumoto, Keiya Sato
In recent years, large language models (LLMs) have rapidly proliferated and have been utilized in various tasks, including research in dialogue systems. We aimed to construct a system that not only leverages the flexible conversational abilities of LLMs but also their advanced planning capabilities to reduce the speaking load on human interlocutors and efficiently plan trips. Furthermore, we propose a method that divides the complex task of a travel agency into multiple subtasks, managing each as a separate phase to effectively accomplish the task. Our proposed system confirmed a certain level of success by achieving fourth place in the Dialogue Robot Competition 2023 preliminaries rounds. We report on the challenges identified through the competition.