Authors: Weijie Xu, Jay Desai, Srinivasan Sengamedu, Xiaoyu Jiang, Francis Iannacci
Language model based methods are powerful techniques for text classification. However, the models have several shortcomings. (1) It is difficult to integrate human knowledge such as keywords. (2) It needs a lot of resources to train the models. (3) It relied on large text data to pretrain. In this paper, we propose Semi-Supervised vMF Neural Topic Modeling (S2vNTM) to overcome these difficulties. S2vNTM takes a few seed keywords as input for topics. S2vNTM leverages the pattern of keywords to identify potential topics, as well as optimize the quality of topics' keywords sets. Across a variety of datasets, S2vNTM outperforms existing semi-supervised topic modeling methods in classification accuracy with limited keywords provided. S2vNTM is at least twice as fast as baselines.
Authors: Michael O'Neill, Mark Connor
We present this article as a small gesture in an attempt to counter what appears to be exponentially growing hype around Artificial Intelligence (AI) and its capabilities, and the distraction provided by the associated talk of science-fiction scenarios that might arise if AI should become sentient and super-intelligent. It may also help those outside of the field to become more informed about some of the limitations of AI technology. In the current context of popular discourse AI defaults to mean foundation and large language models (LLMs) such as those used to create ChatGPT. This in itself is a misrepresentation of the diversity, depth and volume of research, researchers, and technology that truly represents the field of AI. AI being a field of research that has existed in software artefacts since at least the 1950's. We set out to highlight a number of limitations of LLMs, and in so doing highlight that harms have already arisen and will continue to arise due to these limitations. Along the way we also highlight some of the associated risks for individuals and organisations in using this technology.
Authors: Siting Xu, Yunlong Tang, Feng Zheng
Launchpad is a musical instrument that allows users to create and perform music by pressing illuminated buttons. To assist and inspire the design of the Launchpad light effect, and provide a more accessible approach for beginners to create music visualization with this instrument, we proposed the LaunchpadGPT model to generate music visualization designs on Launchpad automatically. Based on the language model with excellent generation ability, our proposed LaunchpadGPT takes an audio piece of music as input and outputs the lighting effects of Launchpad-playing in the form of a video (Launchpad-playing video). We collect Launchpad-playing videos and process them to obtain music and corresponding video frame of Launchpad-playing as prompt-completion pairs, to train the language model. The experiment result shows the proposed method can create better music visualization than random generation methods and hold the potential for a broader range of music visualization applications. Our code is available at https://github.com/yunlong10/LaunchpadGPT/.
Authors: El Mehdi Chouham, Jessica López Espejel, Mahaman Sanoussi Yahaya Alassan, Walid Dahhane, El Hassane Ettifouri
The field of programming has a diversity of paradigms that are used according to the working framework. While current neural code generation methods are able to learn and generate code directly from text, we believe that this approach is not optimal for certain code tasks, particularly the generation of classes in an object-oriented project. Specifically, we use natural language processing techniques to extract structured information from requirements descriptions, in order to automate the generation of CRUD (Create, Read, Update, Delete) class code. To facilitate this process, we introduce a pipeline for extracting entity and relation information, as well as a representation called an "Entity Tree" to model this information. We also create a dataset to evaluate the effectiveness of our approach.
Authors: Bhathiya Hemanthage, Christian Dondrup, Phil Bartie, Oliver Lemon
SimpleMTOD is a simple language model which recasts several sub-tasks in multimodal task-oriented dialogues as sequence prediction tasks. SimpleMTOD is built on a large-scale transformer-based auto-regressive architecture, which has already proven to be successful in uni-modal task-oriented dialogues, and effectively leverages transfer learning from pre-trained GPT-2. In-order to capture the semantics of visual scenes, we introduce both local and de-localized tokens for objects within a scene. De-localized tokens represent the type of an object rather than the specific object itself and so possess a consistent meaning across the dataset. SimpleMTOD achieves a state-of-the-art BLEU score (0.327) in the Response Generation sub-task of the SIMMC 2.0 test-std dataset while performing on par in other multimodal sub-tasks: Disambiguation, Coreference Resolution, and Dialog State Tracking. This is despite taking a minimalist approach for extracting visual (and non-visual) information. In addition the model does not rely on task-specific architectural changes such as classification heads.
Authors: Simin Chen, Shiyi Wei, Cong Liu, Wei Yang
DL compiler's primary function is to translate DNN programs written in high-level DL frameworks such as PyTorch and TensorFlow into portable executables. These executables can then be flexibly executed by the deployed host programs. However, existing DL compilers rely on a tracing mechanism, which involves feeding a runtime input to a neural network program and tracing the program execution paths to generate the computational graph necessary for compilation. Unfortunately, this mechanism falls short when dealing with modern dynamic neural networks (DyNNs) that possess varying computational graphs depending on the inputs. Consequently, conventional DL compilers struggle to accurately compile DyNNs into executable code. To address this limitation, we propose \tool, a general approach that enables any existing DL compiler to successfully compile DyNNs. \tool tackles the dynamic nature of DyNNs by introducing a compilation mechanism that redistributes the control and data flow of the original DNN programs during the compilation process. Specifically, \tool develops program analysis and program transformation techniques to convert a dynamic neural network into multiple sub-neural networks. Each sub-neural network is devoid of conditional statements and is compiled independently. Furthermore, \tool synthesizes a host module that models the control flow of the DyNNs and facilitates the invocation of the sub-neural networks. Our evaluation demonstrates the effectiveness of \tool, achieving a 100\% success rate in compiling all dynamic neural networks. Moreover, the compiled executables generated by \tool exhibit significantly improved performance, running between $1.12\times$ and $20.21\times$ faster than the original DyNNs executed on general-purpose DL frameworks.
Authors: Rui Zheng, Shihan Dou, Songyang Gao, Wei Shen, Binghai Wang, Yan Liu, Senjie Jin, Qin Liu, Limao Xiong, Lu Chen, Zhiheng Xi, Yuhao Zhou, Nuo Xu, Wenbin Lai, Minghao Zhu, Rongxiang Weng, Wensen Cheng, Cheng Chang, Zhangyue Yin, Yuan Hua, Haoran Huang, Tianxiang Sun, Hang Yan, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang
Large language models (LLMs) have formulated a blueprint for the advancement of artificial general intelligence. Its primary objective is to function as a human-centric (helpful, honest, and harmless) assistant. Alignment with humans assumes paramount significance, and reinforcement learning with human feedback (RLHF) emerges as the pivotal technological paradigm underpinning this pursuit. Current technical routes usually include \textbf{reward models} to measure human preferences, \textbf{Proximal Policy Optimization} (PPO) to optimize policy model outputs, and \textbf{process supervision} to improve step-by-step reasoning capabilities. However, due to the challenges of reward design, environment interaction, and agent training, coupled with huge trial and error cost of large language models, there is a significant barrier for AI researchers to motivate the development of technical alignment and safe landing of LLMs. The stable training of RLHF has still been a puzzle. In the first report, we dissect the framework of RLHF, re-evaluate the inner workings of PPO, and explore how the parts comprising PPO algorithms impact policy agent training. We identify policy constraints being the key factor for the effective implementation of the PPO algorithm. Therefore, we explore the PPO-max, an advanced version of PPO algorithm, to efficiently improve the training stability of the policy model. Based on our main results, we perform a comprehensive analysis of RLHF abilities compared with SFT models and ChatGPT. The absence of open-source implementations has posed significant challenges to the investigation of LLMs alignment. Therefore, we are eager to release technical reports, reward models and PPO codes
Authors: Vinit S. Unni, Ashish Mittal, Preethi Jyothi, Sunita Sarawagi
RNN-Transducers (RNN-Ts) have gained widespread acceptance as an end-to-end model for speech to text conversion because of their high accuracy and streaming capabilities. A typical RNN-T independently encodes the input audio and the text context, and combines the two encodings by a thin joint network. While this architecture provides SOTA streaming accuracy, it also makes the model vulnerable to strong LM biasing which manifests as multi-step hallucination of text without acoustic evidence. In this paper we propose LookAhead that makes text representations more acoustically grounded by looking ahead into the future within the audio input. This technique yields a significant 5%-20% relative reduction in word error rate on both in-domain and out-of-domain evaluation sets.
Authors: Sushma Anand Akoju, Robert Vacareanu, Haris Riaz, Eduardo Blanco, Mihai Surdeanu
We introduce a synthetic dataset called Sentences Involving Complex Compositional Knowledge (SICCK) and a novel analysis that investigates the performance of Natural Language Inference (NLI) models to understand compositionality in logic. We produce 1,304 sentence pairs by modifying 15 examples from the SICK dataset (Marelli et al., 2014). To this end, we modify the original texts using a set of phrases - modifiers that correspond to universal quantifiers, existential quantifiers, negation, and other concept modifiers in Natural Logic (NL) (MacCartney, 2009). We use these phrases to modify the subject, verb, and object parts of the premise and hypothesis. Lastly, we annotate these modified texts with the corresponding entailment labels following NL rules. We conduct a preliminary verification of how well the change in the structural and semantic composition is captured by neural NLI models, in both zero-shot and fine-tuned scenarios. We found that the performance of NLI models under the zero-shot setting is poor, especially for modified sentences with negation and existential quantifiers. After fine-tuning this dataset, we observe that models continue to perform poorly over negation, existential and universal modifiers.
Authors: Zongxia Li, Paiheng Xu, Fuxiao Liu, Hyemi Song
We investigate the role of various demonstration components in the in-context learning (ICL) performance of large language models (LLMs). Specifically, we explore the impacts of ground-truth labels, input distribution, and complementary explanations, particularly when these are altered or perturbed. We build on previous work, which offers mixed findings on how these elements influence ICL. To probe these questions, we employ explainable NLP (XNLP) methods and utilize saliency maps of contrastive demonstrations for both qualitative and quantitative analysis. Our findings reveal that flipping ground-truth labels significantly affects the saliency, though it's more noticeable in larger LLMs. Our analysis of the input distribution at a granular level reveals that changing sentiment-indicative terms in a sentiment analysis task to neutral ones does not have as substantial an impact as altering ground-truth labels. Finally, we find that the effectiveness of complementary explanations in boosting ICL performance is task-dependent, with limited benefits seen in sentiment analysis tasks compared to symbolic reasoning tasks. These insights are critical for understanding the functionality of LLMs and guiding the development of effective demonstrations, which is increasingly relevant in light of the growing use of LLMs in applications such as ChatGPT. Our research code is publicly available at https://github.com/paihengxu/XICL.
Authors: Huihui Xu, Kevin Ashley
We use the combination of argumentative zoning [1] and a legal argumentative scheme to create legal argumentative segments. Based on the argumentative segmentation, we propose a novel task of classifying argumentative segments of legal case decisions. GPT-3.5 is used to generate summaries based on argumentative segments. In terms of automatic evaluation metrics, our method generates higher quality argumentative summaries while leaving out less relevant context as compared to GPT-4 and non-GPT models.
Authors: Oleksandr Palagin, Vladislav Kaverinskiy, Anna Litvin, Kyrylo Malakhov
This research presents a comprehensive methodology for utilizing an ontology-driven structured prompts system in interplay with ChatGPT, a widely used large language model (LLM). The study develops formal models, both information and functional, and establishes the methodological foundations for integrating ontology-driven prompts with ChatGPT's meta-learning capabilities. The resulting productive triad comprises the methodological foundations, advanced information technology, and the OntoChatGPT system, which collectively enhance the effectiveness and performance of chatbot systems. The implementation of this technology is demonstrated using the Ukrainian language within the domain of rehabilitation. By applying the proposed methodology, the OntoChatGPT system effectively extracts entities from contexts, classifies them, and generates relevant responses. The study highlights the versatility of the methodology, emphasizing its applicability not only to ChatGPT but also to other chatbot systems based on LLMs, such as Google's Bard utilizing the PaLM 2 LLM. The underlying principles of meta-learning, structured prompts, and ontology-driven information retrieval form the core of the proposed methodology, enabling their adaptation and utilization in various LLM-based systems. This versatile approach opens up new possibilities for NLP and dialogue systems, empowering developers to enhance the performance and functionality of chatbot systems across different domains and languages.
Authors: Pramit Bhattacharyya, Joydeep Mondal, Subhadip Maji, Arnab Bhattacharya
Bangla (or Bengali) is the fifth most spoken language globally; yet, the state-of-the-art NLP in Bangla is lagging for even simple tasks such as lemmatization, POS tagging, etc. This is partly due to lack of a varied quality corpus. To alleviate this need, we build Vacaspati, a diverse corpus of Bangla literature. The literary works are collected from various websites; only those works that are publicly available without copyright violations or restrictions are collected. We believe that published literature captures the features of a language much better than newspapers, blogs or social media posts which tend to follow only a certain literary pattern and, therefore, miss out on language variety. Our corpus Vacaspati is varied from multiple aspects, including type of composition, topic, author, time, space, etc. It contains more than 11 million sentences and 115 million words. We also built a word embedding model, Vac-FT, using FastText from Vacaspati as well as trained an Electra model, Vac-BERT, using the corpus. Vac-BERT has far fewer parameters and requires only a fraction of resources compared to other state-of-the-art transformer models and yet performs either better or similar on various downstream tasks. On multiple downstream tasks, Vac-FT outperforms other FastText-based models. We also demonstrate the efficacy of Vacaspati as a corpus by showing that similar models built from other corpora are not as effective. The models are available at https://bangla.iitk.ac.in/.
Authors: Zhouhong Gu, Zihan Li, Lin Zhang, Zhuozhi Xiong, Sihang Jiang, Xiaoxuan Zhu, Shusen Wang, Zili Wang, Jianchen Wang, Haoning Ye, Wenhao Huang, Yikai Zhang, Hongwei Feng, Yanghua Xiao
This paper introduces the Life Scapes Reasoning Benchmark (LSR-Benchmark), a novel dataset targeting real-life scenario reasoning, aiming to close the gap in artificial neural networks' ability to reason in everyday contexts. In contrast to domain knowledge reasoning datasets, LSR-Benchmark comprises free-text formatted questions with rich information on real-life scenarios, human behaviors, and character roles. The dataset consists of 2,162 questions collected from open-source online sources and is manually annotated to improve its quality. Experiments are conducted using state-of-the-art language models, such as gpt3.5-turbo and instruction fine-tuned llama models, to test the performance in LSR-Benchmark. The results reveal that humans outperform these models significantly, indicating a persisting challenge for machine learning models in comprehending daily human life.
Authors: Anastasios Nentidis, Georgios Katsimpras, Anastasia Krithara, Salvador Lima López, Eulália Farré-Maduell, Luis Gasco, Martin Krallinger, Georgios Paliouras
This is an overview of the eleventh edition of the BioASQ challenge in the context of the Conference and Labs of the Evaluation Forum (CLEF) 2023. BioASQ is a series of international challenges promoting advances in large-scale biomedical semantic indexing and question answering. This year, BioASQ consisted of new editions of the two established tasks b and Synergy, and a new task (MedProcNER) on semantic annotation of clinical content in Spanish with medical procedures, which have a critical role in medical practice. In this edition of BioASQ, 28 competing teams submitted the results of more than 150 distinct systems in total for the three different shared tasks of the challenge. Similarly to previous editions, most of the participating systems achieved competitive performance, suggesting the continuous advancement of the state-of-the-art in the field.
Authors: Paul Grimal, Hervé Le Borgne, Olivier Ferret, Julien Tourille
The progress in the generation of synthetic images has made it crucial to assess their quality. While several metrics have been proposed to assess the rendering of images, it is crucial for Text-to-Image (T2I) models, which generate images based on a prompt, to consider additional aspects such as to which extent the generated image matches the important content of the prompt. Moreover, although the generated images usually result from a random starting point, the influence of this one is generally not considered. In this article, we propose a new metric based on prompt templates to study the alignment between the content specified in the prompt and the corresponding generated images. It allows us to better characterize the alignment in terms of the type of the specified objects, their number, and their color. We conducted a study on several recent T2I models about various aspects. An additional interesting result we obtained with our approach is that image quality can vary drastically depending on the latent noise used as a seed for the images. We also quantify the influence of the number of concepts in the prompt, their order as well as their (color) attributes. Finally, our method allows us to identify some latent seeds that produce better images than others, opening novel directions of research on this understudied topic.
Authors: Kunal Suri, Prakhar Mishra, Saumajit Saha, Atul Singh
Finetuning Large Language Models helps improve the results for domain-specific use cases. End-to-end finetuning of large language models is time and resource intensive and has high storage requirements to store the finetuned version of the large language model. Parameter Efficient Fine Tuning (PEFT) methods address the time and resource challenges by keeping the large language model as a fixed base and add additional layers, which the PEFT methods finetune. This paper demonstrates the evaluation results for one such PEFT method Low Rank Adaptation (LoRA), for Clinical Dialogue Summarization. The evaluation results show that LoRA works at par with end-to-end finetuning for a large language model. The paper presents the evaluations done for solving both the Subtask A and B from ImageCLEFmedical {https://www.imageclef.org/2023/medical}
Authors: Che Zhang, Ping'an Liu, Zhenyang Xiao, Haojun Fei
The study of human values is essential in both practical and theoretical domains. With the development of computational linguistics, the creation of large-scale datasets has made it possible to automatically recognize human values accurately. SemEval 2023 Task 4\cite{kiesel:2023} provides a set of arguments and 20 types of human values that are implicitly expressed in each argument. In this paper, we present our team's solution. We use the Roberta\cite{liu_roberta_2019} model to obtain the word vector encoding of the document and propose a multi-head attention mechanism to establish connections between specific labels and semantic components. Furthermore, we use a contrastive learning-enhanced K-nearest neighbor mechanism\cite{su_contrastive_2022} to leverage existing instance information for prediction. Our approach achieved an F1 score of 0.533 on the test set and ranked fourth on the leaderboard.
Authors: Runcheng Liu, Ahmad Rashid, Ivan Kobyzev, Mehdi Rezagholizadeh, Pascal Poupart
Prompt-tuning has become an increasingly popular parameter-efficient method for adapting large pretrained language models to downstream tasks. However, both discrete prompting and continuous prompting assume fixed prompts for all data samples within a task, neglecting the fact that inputs vary greatly in some tasks such as open-domain dialogue generation. In this paper, we present a novel, instance-specific prompt-tuning algorithm for dialogue generation. Specifically, we generate prompts based on instance-level control code, rather than the conversation history, to explore their impact on controlled dialogue generation. Experiments on popular open-domain dialogue datasets, evaluated on both automated metrics and human evaluation, demonstrate that our method is superior to prompting baselines and comparable to fine-tuning with only 5%-6% of total parameters.
Authors: Abhinav Joshi, Akshat Sharma, Sai Kiran Tanikella, Ashutosh Modi
The task of Prior Case Retrieval (PCR) in the legal domain is about automatically citing relevant (based on facts and precedence) prior legal cases in a given query case. To further promote research in PCR, in this paper, we propose a new large benchmark (in English) for the PCR task: IL-PCR (Indian Legal Prior Case Retrieval) corpus. Given the complex nature of case relevance and the long size of legal documents, BM25 remains a strong baseline for ranking the cited prior documents. In this work, we explore the role of events in legal case retrieval and propose an unsupervised retrieval method-based pipeline U-CREAT (Unsupervised Case Retrieval using Events Extraction). We find that the proposed unsupervised retrieval method significantly increases performance compared to BM25 and makes retrieval faster by a considerable margin, making it applicable to real-time case retrieval systems. Our proposed system is generic, we show that it generalizes across two different legal systems (Indian and Canadian), and it shows state-of-the-art performance on the benchmarks for both the legal systems (IL-PCR and COLIEE corpora).
Authors: Zhenhailong Wang, Shaoguang Mao, Wenshan Wu, Tao Ge, Furu Wei, Heng Ji
Human intelligence thrives on the concept of cognitive synergy, where collaboration and information integration among different cognitive processes yield superior outcomes compared to individual cognitive processes in isolation. Although Large Language Models (LLMs) have demonstrated promising performance as general task-solving agents, they still struggle with tasks that require intensive domain knowledge and complex reasoning. In this work, we propose Solo Performance Prompting (SPP), which transforms a single LLM into a cognitive synergist by engaging in multi-turn self-collaboration with multiple personas. A cognitive synergist refers to an intelligent agent that collaborates with multiple minds, combining their individual strengths and knowledge, to enhance problem-solving and overall performance in complex tasks. By dynamically identifying and simulating different personas based on task inputs, SPP unleashes the potential of cognitive synergy in LLMs. We have discovered that assigning multiple, fine-grained personas in LLMs elicits better problem-solving abilities compared to using a single or fixed number of personas. We evaluate SPP on three challenging tasks: Trivia Creative Writing, Codenames Collaborative, and Logic Grid Puzzle, encompassing both knowledge-intensive and reasoning-intensive types. Unlike previous works, such as Chain-of-Thought, that solely enhance the reasoning abilities in LLMs, SPP effectively elicits internal knowledge acquisition abilities, reduces hallucination, and maintains strong reasoning capabilities. Code, data, and prompts can be found at: https://github.com/MikeWangWZHL/Solo-Performance-Prompting.git.
Authors: Melody Yu
In this paper, we analyze the character networks extracted from three popular television series and explore the relationship between a TV show episode's character network metrics and its review from IMDB. Character networks are graphs created from the plot of a TV show that represents the interactions of characters in scenes, indicating the presence of a connection between them. We calculate various network metrics for each episode, such as node degree and graph density, and use these metrics to explore the potential relationship between network metrics and TV series reviews from IMDB. Our results show that certain network metrics of character interactions in episodes have a strong correlation with the review score of TV series. Our research aims to provide more quantitative information that can help TV producers understand how to adjust the character dynamics of future episodes to appeal to their audience. By understanding the impact of character interactions on audience engagement and enjoyment, producers can make informed decisions about the development of their shows.
Authors: Jierui Li, Szymon Tworkowski, Yingying Wu, Raymond Mooney
In this paper, we approach competitive-level programming problem-solving as a composite task of reasoning and code generation. We propose a novel method to automatically annotate natural language explanations to \textit{<problem, solution>} pairs. We show that despite poor performance in solving competitive-level programming problems, state-of-the-art LLMs exhibit a strong capacity in describing and explaining solutions. Our explanation generation methodology can generate a structured solution explanation for the problem containing descriptions and analysis. To evaluate the quality of the annotated explanations, we examine their effectiveness in two aspects: 1) satisfying the human programming expert who authored the oracle solution, and 2) aiding LLMs in solving problems more effectively. The experimental results on the CodeContests dataset demonstrate that while LLM GPT3.5's and GPT-4's abilities in describing the solution are comparable, GPT-4 shows a better understanding of the key idea behind the solution.
Authors: Dongbo Wang, Chang Liu, Zhixiao Zhao, Si Shen, Liu Liu, Bin Li, Haotian Hu, Mengcheng Wu, Litao Lin, Xue Zhao, Xiyu Wang
In the context of the rapid development of large language models, we have meticulously trained and introduced the GujiBERT and GujiGPT language models, which are foundational models specifically designed for intelligent information processing of ancient texts. These models have been trained on an extensive dataset that encompasses both simplified and traditional Chinese characters, allowing them to effectively handle various natural language processing tasks related to ancient books, including but not limited to automatic sentence segmentation, punctuation, word segmentation, part-of-speech tagging, entity recognition, and automatic translation. Notably, these models have exhibited exceptional performance across a range of validation tasks using publicly available datasets. Our research findings highlight the efficacy of employing self-supervised methods to further train the models using classical text corpora, thus enhancing their capability to tackle downstream tasks. Moreover, it is worth emphasizing that the choice of font, the scale of the corpus, and the initial model selection all exert significant influence over the ultimate experimental outcomes. To cater to the diverse text processing preferences of researchers in digital humanities and linguistics, we have developed three distinct categories comprising a total of nine model variations. We believe that by sharing these foundational language models specialized in the domain of ancient texts, we can facilitate the intelligent processing and scholarly exploration of ancient literary works and, consequently, contribute to the global dissemination of China's rich and esteemed traditional culture in this new era.
Authors: Nuwa Xi, Sendong Zhao, Haochun Wang, Chi Liu, Bing Qin, Ting Liu
Decoding text stimuli from cognitive signals (e.g. fMRI) enhances our understanding of the human language system, paving the way for building versatile Brain-Computer Interface. However, existing studies largely focus on decoding individual word-level fMRI volumes from a restricted vocabulary, which is far too idealized for real-world application. In this paper, we propose fMRI2text, the first openvocabulary task aiming to bridge fMRI time series and human language. Furthermore, to explore the potential of this new task, we present a baseline solution, UniCoRN: the Unified Cognitive Signal ReconstructioN for Brain Decoding. By reconstructing both individual time points and time series, UniCoRN establishes a robust encoder for cognitive signals (fMRI & EEG). Leveraging a pre-trained language model as decoder, UniCoRN proves its efficacy in decoding coherent text from fMRI series across various split settings. Our model achieves a 34.77% BLEU score on fMRI2text, and a 37.04% BLEU when generalized to EEGto-text decoding, thereby surpassing the former baseline. Experimental results indicate the feasibility of decoding consecutive fMRI volumes, and the effectiveness of decoding different cognitive signals using a unified structure.
Authors: Sayed Erfan Arefin, Tasnia Ashrafi Heya, Hasan Al-Qudah, Ynes Ineza, Abdul Serwadda
The transformative influence of Large Language Models (LLMs) is profoundly reshaping the Artificial Intelligence (AI) technology domain. Notably, ChatGPT distinguishes itself within these models, demonstrating remarkable performance in multi-turn conversations and exhibiting code proficiency across an array of languages. In this paper, we carry out a comprehensive evaluation of ChatGPT's coding capabilities based on what is to date the largest catalog of coding challenges. Our focus is on the python programming language and problems centered on data structures and algorithms, two topics at the very foundations of Computer Science. We evaluate ChatGPT for its ability to generate correct solutions to the problems fed to it, its code quality, and nature of run-time errors thrown by its code. Where ChatGPT code successfully executes, but fails to solve the problem at hand, we look into patterns in the test cases passed in order to gain some insights into how wrong ChatGPT code is in these kinds of situations. To infer whether ChatGPT might have directly memorized some of the data that was used to train it, we methodically design an experiment to investigate this phenomena. Making comparisons with human performance whenever feasible, we investigate all the above questions from the context of both its underlying learning models (GPT-3.5 and GPT-4), on a vast array sub-topics within the main topics, and on problems having varying degrees of difficulty.
Authors: Thales Sales Almeida, Thiago Laitz, Giovana K. Bonás, Rodrigo Nogueira
One common trend in recent studies of language models (LMs) is the use of standardized tests for evaluation. However, despite being the fifth most spoken language worldwide, few such evaluations have been conducted in Portuguese. This is mainly due to the lack of high-quality datasets available to the community for carrying out evaluations in Portuguese. To address this gap, we introduce the Brazilian Leading Universities Entrance eXams (BLUEX), a dataset of entrance exams from the two leading universities in Brazil: UNICAMP and USP. The dataset includes annotated metadata for evaluating the performance of NLP models on a variety of subjects. Furthermore, BLUEX includes a collection of recently administered exams that are unlikely to be included in the training data of many popular LMs as of 2023. The dataset is also annotated to indicate the position of images in each question, providing a valuable resource for advancing the state-of-the-art in multimodal language understanding and reasoning. We describe the creation and characteristics of BLUEX and establish a benchmark through experiments with state-of-the-art LMs, demonstrating its potential for advancing the state-of-the-art in natural language understanding and reasoning in Portuguese. The data and relevant code can be found at https://github.com/Portuguese-Benchmark-Datasets/BLUEX
Authors: Changshang Xue
This paper investigates the employment of various encoders in text transformation, converting characters into bytes. It discusses local encoders such as ASCII and GB-2312, which encode specific characters into shorter bytes, and universal encoders like UTF-8 and UTF-16, which can encode the complete Unicode set with greater space requirements and are gaining widespread acceptance. Other encoders, including SCSU, BOCU-1, and binary encoders, however, lack self-synchronizing capabilities. Duncode is introduced as an innovative encoding method that aims to encode the entire Unicode character set with high space efficiency, akin to local encoders. It has the potential to compress multiple characters of a string into a Duncode unit using fewer bytes. Despite offering less self-synchronizing identification information, Duncode surpasses UTF8 in terms of space efficiency. The application is available at \url{https://github.com/laohur/duncode}. Additionally, we have developed a benchmark for evaluating character encoders across different languages. It encompasses 179 languages and can be accessed at \url{https://github.com/laohur/wiki2txt}.
Authors: Abhinav Joshi, Susmit Agrawal, Ashutosh Modi
Sign languages are the primary means of communication for many hard-of-hearing people worldwide. Recently, to bridge the communication gap between the hard-of-hearing community and the rest of the population, several sign language translation datasets have been proposed to enable the development of statistical sign language translation systems. However, there is a dearth of sign language resources for the Indian sign language. This resource paper introduces ISLTranslate, a translation dataset for continuous Indian Sign Language (ISL) consisting of 31k ISL-English sentence/phrase pairs. To the best of our knowledge, it is the largest translation dataset for continuous Indian Sign Language. We provide a detailed analysis of the dataset. To validate the performance of existing end-to-end Sign language to spoken language translation systems, we benchmark the created dataset with a transformer-based model for ISL translation.
Authors: Ester Hlavnova, Sebastian Ruder
A challenge towards developing NLP systems for the world's languages is understanding how they generalize to typological differences relevant for real-world applications. To this end, we propose M2C, a morphologically-aware framework for behavioral testing of NLP models. We use M2C to generate tests that probe models' behavior in light of specific linguistic features in 12 typologically diverse languages. We evaluate state-of-the-art language models on the generated tests. While models excel at most tests in English, we highlight generalization failures to specific typological characteristics such as temporal expressions in Swahili and compounding possessives in Finish. Our findings motivate the development of models that address these blind spots.
Authors: Shammur Absar Chowdhury, Nadir Durrani, Ahmed Ali
Deep neural networks are inherently opaque and challenging to interpret. Unlike hand-crafted feature-based models, we struggle to comprehend the concepts learned and how they interact within these models. This understanding is crucial not only for debugging purposes but also for ensuring fairness in ethical decision-making. In our study, we conduct a post-hoc functional interpretability analysis of pretrained speech models using the probing framework [1]. Specifically, we analyze utterance-level representations of speech models trained for various tasks such as speaker recognition and dialect identification. We conduct layer and neuron-wise analyses, probing for speaker, language, and channel properties. Our study aims to answer the following questions: i) what information is captured within the representations? ii) how is it represented and distributed? and iii) can we identify a minimal subset of the network that possesses this information?
Our results reveal several novel findings, including: i) channel and gender information are distributed across the network, ii) the information is redundantly available in neurons with respect to a task, iii) complex properties such as dialectal information are encoded only in the task-oriented pretrained network, iv) and is localised in the upper layers, v) we can extract a minimal subset of neurons encoding the pre-defined property, vi) salient neurons are sometimes shared between properties, vii) our analysis highlights the presence of biases (for example gender) in the network. Our cross-architectural comparison indicates that: i) the pretrained models capture speaker-invariant information, and ii) CNN models are competitive with Transformer models in encoding various understudied properties.
Authors: Yulin Chen, Beishui Liao, Bruno Bentzen, Bo Yuan, Zelai Yao, Haixiao Chi, Dov Gabbay
As one of the basic tasks in natural language processing (NLP), named entity recognition (NER) is an important basic tool for downstream tasks of NLP, such as information extraction, syntactic analysis, machine translation and so on. The internal operation logic of current name entity recognition model is black-box to the user, so the user has no basis to determine which name entity makes more sense. Therefore, a user-friendly explainable recognition process would be very useful for many people. In this paper, we propose a novel interpretable method, BTPK (Binary Talmudic Public Announcement Logic model), to help users understand the internal recognition logic of the name entity recognition tasks based on Talmudic Public Announcement Logic. BTPK model can also capture the semantic information in the input sentences, that is, the context dependency of the sentence. We observed the public announcement of BTPK presents the inner decision logic of BRNNs, and the explanations obtained from a BTPK model show us how BRNNs essentially handle NER tasks.
Authors: Siddharth Dalmia, Dmytro Okhonko, Mike Lewis, Sergey Edunov, Shinji Watanabe, Florian Metze, Luke Zettlemoyer, Abdelrahman Mohamed
State-of-the-art encoder-decoder models (e.g. for machine translation (MT) or automatic speech recognition (ASR)) are constructed and trained end-to-end as an atomic unit. No component of the model can be (re-)used without the others, making it impossible to share parts, e.g. a high resourced decoder, across tasks. We describe LegoNN, a procedure for building encoder-decoder architectures in a way so that its parts can be applied to other tasks without the need for any fine-tuning. To achieve this reusability, the interface between encoder and decoder modules is grounded to a sequence of marginal distributions over a pre-defined discrete vocabulary. We present two approaches for ingesting these marginals; one is differentiable, allowing the flow of gradients across the entire network, and the other is gradient-isolating. To enable the portability of decoder modules between MT tasks for different source languages and across other tasks like ASR, we introduce a modality agnostic encoder which consists of a length control mechanism to dynamically adapt encoders' output lengths in order to match the expected input length range of pre-trained decoders. We present several experiments to demonstrate the effectiveness of LegoNN models: a trained language generation LegoNN decoder module from German-English (De-En) MT task can be reused without any fine-tuning for the Europarl English ASR and the Romanian-English (Ro-En) MT tasks, matching or beating the performance of baseline. After fine-tuning, LegoNN models improve the Ro-En MT task by 1.5 BLEU points and achieve 12.5% relative WER reduction on the Europarl ASR task. To show how the approach generalizes, we compose a LegoNN ASR model from three modules -- each has been learned within different end-to-end trained models on three different datasets -- achieving an overall WER reduction of 19.5%.
Authors: Nilay Patel, Jeffrey Flanigan
Human language is known to exhibit a nested, hierarchical structure, allowing us to form complex sentences out of smaller pieces. However, many state-of-the-art neural networks models such as Transformers have no explicit hierarchical structure in its architecture -- that is, they don't have an inductive bias toward hierarchical structure. Additionally, Transformers are known to perform poorly on compositional generalization tasks which require such structures. In this paper, we introduce Treeformer, a general-purpose encoder module inspired by the CKY algorithm which learns a composition operator and pooling function to construct hierarchical encodings for phrases and sentences. Our extensive experiments demonstrate the benefits of incorporating hierarchical structure into the Transformer and show significant improvements in compositional generalization as well as in downstream tasks such as machine translation, abstractive summarization, and various natural language understanding tasks.
Authors: Zhe Zhao, Yudong Li, Cheng Hou, Jing Zhao, Rong Tian, Weijie Liu, Yiren Chen, Ningyuan Sun, Haoyan Liu, Weiquan Mao, Han Guo, Weigang Guo, Taiqiang Wu, Tao Zhu, Wenhang Shi, Chen Chen, Shan Huang, Sihong Chen, Liqun Liu, Feifei Li, Xiaoshuai Chen, Xingwu Sun, Zhanhui Kang, Xiaoyong Du, Linlin Shen, Kimmo Yan
Recently, the success of pre-training in text domain has been fully extended to vision, audio, and cross-modal scenarios. The proposed pre-training models of different modalities are showing a rising trend of homogeneity in their model structures, which brings the opportunity to implement different pre-training models within a uniform framework. In this paper, we present TencentPretrain, a toolkit supporting pre-training models of different modalities. The core feature of TencentPretrain is the modular design. The toolkit uniformly divides pre-training models into 5 components: embedding, encoder, target embedding, decoder, and target. As almost all of common modules are provided in each component, users can choose the desired modules from different components to build a complete pre-training model. The modular design enables users to efficiently reproduce existing pre-training models or build brand-new one. We test the toolkit on text, vision, and audio benchmarks and show that it can match the performance of the original implementations.
Authors: Qintong Li, Zhiyong Wu, Lingpeng Kong, Wei Bi
Explaining the black-box predictions of NLP models naturally and accurately is an important open problem in natural language generation. These free-text explanations are expected to contain sufficient and carefully-selected evidence to form supportive arguments for predictions. Due to the superior generative capacity of large pretrained language models, recent work built on prompt engineering enables explanation generation without specific training. However, explanation generated through single-pass prompting often lacks sufficiency and conciseness. To address this problem, we develop an information bottleneck method EIB to produce refined explanations that are sufficient and concise. Our approach regenerates the free-text explanation by polishing the single-pass output from the pretrained language model but retaining the information that supports the contents being explained. Experiments on two out-of-domain tasks verify the effectiveness of EIB through automatic evaluation and thoroughly-conducted human evaluation.
Authors: Ercong Nie, Sheng Liang, Helmut Schmid, Hinrich Schütze
Multilingual Pretrained Language Models (MPLMs) have shown their strong multilinguality in recent empirical cross-lingual transfer studies. In this paper, we propose the Prompts Augmented by Retrieval Crosslingually (PARC) pipeline to improve the zero-shot performance on low-resource languages (LRLs) by augmenting the context with semantically similar sentences retrieved from a high-resource language (HRL) as prompts. PARC improves the zero-shot performance on three downstream tasks (binary sentiment classification, topic categorization and natural language inference) with multilingual parallel test sets across 10 LRLs covering 6 language families in both unlabeled settings (+5.1%) and labeled settings (+16.3%). PARC-labeled also outperforms the finetuning baseline by 3.7%. We find a significant positive correlation between cross-lingual transfer performance on one side, and the similarity between the high- and low-resource languages as well as the amount of low-resource pretraining data on the other side. A robustness analysis suggests that PARC has the potential to achieve even stronger performance with more powerful MPLMs.
Authors: Faisal Ladhak, Esin Durmus, Tatsunori Hashimoto
Recent work has identified noisy and misannotated data as a core cause of hallucinations and unfaithful outputs in Natural Language Generation (NLG) tasks. Consequently, identifying and removing these examples is a key open challenge in creating reliable NLG systems. In this work, we introduce a framework to identify and remove low-quality training instances that lead to undesirable outputs, such as faithfulness errors in text summarization. We show that existing approaches for error tracing, such as gradient-based influence measures, do not perform reliably for detecting faithfulness errors in NLG datasets. We overcome the drawbacks of existing error tracing methods through a new, contrast-based estimate that compares undesired generations to human-corrected outputs. Our proposed method can achieve a mean average precision of 0.93 at detecting known data errors across synthetic tasks with known ground truth, substantially outperforming existing approaches. Using this approach and re-training models on cleaned data leads to a 70% reduction in entity hallucinations on the NYT dataset and a 55% reduction in semantic errors on the E2E dataset.
Authors: Anej Svete, Benjamin Dayan, Tim Vieira, Ryan Cotterell, Jason Eisner
Weighted finite-state automata (WSFAs) are commonly used in NLP. Failure transitions are a useful extension for compactly representing backoffs or interpolation in $n$-gram models and CRFs, which are special cases of WFSAs. The pathsum in ordinary acyclic WFSAs is efficiently computed by the backward algorithm in time $O(|E|)$, where $E$ is the set of transitions. However, this does not allow failure transitions, and preprocessing the WFSA to eliminate failure transitions could greatly increase $|E|$. We extend the backward algorithm to handle failure transitions directly. Our approach is efficient when the average state has outgoing arcs for only a small fraction $s \ll 1$ of the alphabet $\Sigma$. We propose an algorithm for general acyclic WFSAs which runs in $O{\left(|E| + s |\Sigma| |Q| T_\text{max} \log{|\Sigma|}\right)}$, where $Q$ is the set of states and $T_\text{max}$ is the size of the largest connected component of failure transitions. When the failure transition topology satisfies a condition exemplified by CRFs, the $T_\text{max}$ factor can be dropped, and when the weight semiring is a ring, the $\log{|\Sigma|}$ factor can be dropped. In the latter case (ring-weighted acyclic WFSAs), we also give an alternative algorithm with complexity $\displaystyle O{\left(|E| + |\Sigma| |Q| \min(1,s\pi_\text{max}) \right)}$, where $\pi_\text{max}$ is the size of the longest failure path.
Authors: Tejas Srinivasan, Furong Jia, Mohammad Rostami, Jesse Thomason
Adapters present a promising solution to the catastrophic forgetting problem in continual learning. However, training independent Adapter modules for every new task misses an opportunity for cross-task knowledge transfer. We propose Improvise to Initialize (I2I), a continual learning algorithm that initializes Adapters for incoming tasks by distilling knowledge from previously-learned tasks' Adapters. We evaluate I2I on CLiMB, a multimodal continual learning benchmark, by conducting experiments on sequences of visual question answering tasks. Adapters trained with I2I consistently achieve better task accuracy than independently-trained Adapters, demonstrating that our algorithm facilitates knowledge transfer between task Adapters. I2I also results in better cross-task knowledge transfer than the state-of-the-art AdapterFusion without incurring the associated parametric cost.
Authors: Zhuoer Wang, Marcus Collins, Nikhita Vedula, Simone Filice, Shervin Malmasi, Oleg Rokhlenko
Methods to generate text from structured data have advanced significantly in recent years, primarily due to fine-tuning of pre-trained language models on large datasets. However, such models can fail to produce output faithful to the input data, particularly on out-of-domain data. Sufficient annotated data is often not available for specific domains, leading us to seek an unsupervised approach to improve the faithfulness of output text. Since the problem is fundamentally one of consistency between the representations of the structured data and text, we evaluate the effectiveness of cycle training in this work. Cycle training uses two models which are inverses of each other: one that generates text from structured data, and one which generates the structured data from natural language text. We show that cycle training, when initialized with a small amount of supervised data (100 samples in our case), achieves nearly the same performance as fully supervised approaches for the data-to-text generation task on the WebNLG, E2E, WTQ, and WSQL datasets. We perform extensive empirical analysis with automated evaluation metrics and a newly designed human evaluation schema to reveal different cycle training strategies' effectiveness of reducing various types of generation errors. Our code is publicly available at https://github.com/Edillower/CycleNLG.
Authors: Jiayan Guo, Lun Du, Hengyu Liu, Mengyu Zhou, Xinyi He, Shi Han
Large language models~(LLM) like ChatGPT have become indispensable to artificial general intelligence~(AGI), demonstrating excellent performance in various natural language processing tasks. In the real world, graph data is ubiquitous and an essential part of AGI and prevails in domains like social network analysis, bioinformatics and recommender systems. The training corpus of large language models often includes some algorithmic components, which allows them to achieve certain effects on some graph data-related problems. However, there is still little research on their performance on a broader range of graph-structured data. In this study, we conduct an extensive investigation to assess the proficiency of LLMs in comprehending graph data, employing a diverse range of structural and semantic-related tasks. Our analysis encompasses 10 distinct tasks that evaluate the LLMs' capabilities in graph understanding. Through our study, we not only uncover the current limitations of language models in comprehending graph structures and performing associated reasoning tasks but also emphasize the necessity for further advancements and novel approaches to enhance their graph processing capabilities. Our findings contribute valuable insights towards bridging the gap between language models and graph understanding, paving the way for more effective graph mining and knowledge extraction.
Authors: Baifeng Shi, Siyu Gai, Trevor Darrell, Xin Wang
Transfer learning involves adapting a pre-trained model to novel downstream tasks. However, we observe that current transfer learning methods often fail to focus on task-relevant features. In this work, we explore refocusing model attention for transfer learning. We introduce Top-Down Attention Steering (TOAST), a novel transfer learning algorithm that keeps the pre-trained backbone frozen, selects task-relevant features in the output, and feeds those features back to the model to steer the attention to the task-specific features. By refocusing the attention only, TOAST achieves state-of-the-art results on a number of transfer learning benchmarks, while having a small number of tunable parameters. Compared to fully fine-tuning, LoRA, and prompt tuning, TOAST substantially improves performance across a range of fine-grained visual classification datasets (e.g., 81.1% -> 86.2% on FGVC). TOAST also outperforms the fully fine-tuned Alpaca and Vicuna models on instruction-following language generation. Code is available at https://github.com/bfshi/TOAST.
Authors: Fangzhi Xu, Qika Lin, Jiawei Han, Tianzhe Zhao, Jun Liu, Erik Cambria
Logical reasoning consistently plays a fundamental and significant role in the domains of knowledge engineering and artificial intelligence. Recently, Large Language Models (LLMs) have emerged as a noteworthy innovation in natural language processing (NLP), exhibiting impressive achievements across various classic NLP tasks. However, the question of whether LLMs can effectively address the task of logical reasoning, which requires gradual cognitive inference similar to human intelligence, remains unanswered. To this end, we aim to bridge this gap and provide comprehensive evaluations in this paper. Firstly, to offer systematic evaluations, we select fifteen typical logical reasoning datasets and organize them into deductive, inductive, abductive and mixed-form reasoning settings. Considering the comprehensiveness of evaluations, we include three representative LLMs (i.e., text-davinci-003, ChatGPT and BARD) and evaluate them on all selected datasets under zero-shot, one-shot and three-shot settings. Secondly, different from previous evaluations relying only on simple metrics (e.g., accuracy), we propose fine-level evaluations from objective and subjective manners, covering both answers and explanations. Additionally, to uncover the logical flaws of LLMs, problematic cases will be attributed to five error types from two dimensions, i.e., evidence selection process and reasoning process. Thirdly, to avoid the influences of knowledge bias and purely focus on benchmarking the logical reasoning capability of LLMs, we propose a new dataset with neutral content. It contains 3,000 samples and covers deductive, inductive and abductive settings. Based on the in-depth evaluations, this paper finally forms a general evaluation scheme of logical reasoning capability from six dimensions. It reflects the pros and cons of LLMs and gives guiding directions for future works.
Authors: Brandon Kynoch, Hugo Latapie
The ideal long-term memory mechanism for Large Language Model (LLM) based chatbots, would lay the foundation for continual learning, complex reasoning and allow sequential and temporal dependencies to be learnt. Creating this type of memory mechanism is an extremely challenging problem. In this paper we explore different methods of achieving the effect of long-term memory. We propose a new architecture focused on creating adaptable and updatable long-term memory for AGI systems. We demonstrate through various experiments the benefits of the RecallM architecture, particularly the improved temporal understanding of knowledge it provides.
Authors: Yupeng Chang, Xu Wang, Jindong Wang, Yuan Wu, Kaijie Zhu, Hao Chen, Linyi Yang, Xiaoyuan Yi, Cunxiang Wang, Yidong Wang, Wei Ye, Yue Zhang, Yi Chang, Philip S. Yu, Qiang Yang, Xing Xie
Large language models (LLMs) are gaining increasing popularity in both academia and industry, owing to their unprecedented performance in various applications. As LLMs continue to play a vital role in both research and daily use, their evaluation becomes increasingly critical, not only at the task level, but also at the society level for better understanding of their potential risks. Over the past years, significant efforts have been made to examine LLMs from various perspectives. This paper presents a comprehensive review of these evaluation methods for LLMs, focusing on three key dimensions: what to evaluate, where to evaluate, and how to evaluate. Firstly, we provide an overview from the perspective of evaluation tasks, encompassing general natural language processing tasks, reasoning, medical usage, ethics, educations, natural and social sciences, agent applications, and other areas. Secondly, we answer the `where' and `how' questions by diving into the evaluation methods and benchmarks, which serve as crucial components in assessing performance of LLMs. Then, we summarize the success and failure cases of LLMs in different tasks. Finally, we shed light on several future challenges that lie ahead in LLMs evaluation. Our aim is to offer invaluable insights to researchers in the realm of LLMs evaluation, thereby aiding the development of more proficient LLMs. Our key point is that evaluation should be treated as an essential discipline to better assist the development of LLMs. We consistently maintain the related open-source materials at: https://github.com/MLGroupJLU/LLM-eval-survey.