Tag: cs.CL

Online Personalizing White-box LLMs Generation with Neural Bandits

Zekai Chen, Weeden Daniel, Po-yu Chen, Francois Buet-Golfouse Edit "Online Personalizing White-box LLMs Generation with Neural Bandits"
arXiv:2404.16115v1 Announce Type: new Abstract: The advent of personalized content generation by LLMs presents a novel challenge: how to efficiently adapt text to meet individual preferences without the unsustainable demand of creating a unique model for each user. This study introduces an innovative online method that employs neural bandit algorithms to dynamically optimize soft instruction embeddings based on user feedback, enhancing the personalization of open-ended text generation by white-box LLMs. Through rigorous experimentation on various tasks, we demonstrate significant performance improvements over baseline strategies. NeuralTS, in particular, leads to substantial enhancements in personalized news headline generation, achieving up to a 62.9% improvement in terms of best ROUGE scores and up to 2.76% increase in LLM-agent evaluation against the baseline.

Reinforcement of Explainability of ChatGPT Prompts by Embedding Breast Cancer Self-Screening Rules into AI Responses

Yousef Khan, Ahmed Abdeen Hamed Edit "Reinforcement of Explainability of ChatGPT Prompts by Embedding Breast Cancer Self-Screening Rules into AI Responses"
arXiv:2404.14454v1 Announce Type: new Abstract: Addressing the global challenge of breast cancer, this research explores the fusion of generative AI, focusing on ChatGPT 3.5 turbo model, and the intricacies of breast cancer risk assessment. The research aims to evaluate ChatGPT's reasoning capabilities, emphasizing its potential to process rules and provide explanations for screening recommendations. The study seeks to bridge the technology gap between intelligent machines and clinicians by demonstrating ChatGPT's unique proficiency in natural language reasoning. The methodology employs a supervised prompt-engineering approach to enforce detailed explanations for ChatGPT's recommendations. Synthetic use cases, generated algorithmically, serve as the testing ground for the encoded rules, evaluating the model's processing prowess. Findings highlight ChatGPT's promising capacity in processing rules comparable to Expert System Shells, with a focus on natural language reasoning. The research introduces the concept of reinforcement explainability, showcasing its potential in elucidating outcomes and facilitating user-friendly interfaces for breast cancer risk assessment.

EPI-SQL: Enhancing Text-to-SQL Translation with Error-Prevention Instructions

Xiping Liu, Zhao Tan Edit "EPI-SQL: Enhancing Text-to-SQL Translation with Error-Prevention Instructions"
arXiv:2404.14453v1 Announce Type: new Abstract: The conversion of natural language queries into SQL queries, known as Text-to-SQL, is a critical yet challenging task. This paper introduces EPI-SQL, a novel methodological framework leveraging Large Language Models (LLMs) to enhance the performance of Text-to-SQL tasks. EPI-SQL operates through a four-step process. Initially, the method involves gathering instances from the Spider dataset on which LLMs are prone to failure. These instances are then utilized to generate general error-prevention instructions (EPIs). Subsequently, LLMs craft contextualized EPIs tailored to the specific context of the current task. Finally, these context-specific EPIs are incorporated into the prompt used for SQL generation. EPI-SQL is distinguished in that it provides task-specific guidance, enabling the model to circumvent potential errors for the task at hand. Notably, the methodology rivals the performance of advanced few-shot methods despite being a zero-shot approach. An empirical assessment using the Spider benchmark reveals that EPI-SQL achieves an execution accuracy of 85.1\%, underscoring its effectiveness in generating accurate SQL queries through LLMs. The findings indicate a promising direction for future research, i.e. enhancing instructions with task-specific and contextualized rules, for boosting LLMs' performance in NLP tasks.

Predicting Question Quality on StackOverflow with Neural Networks

Mohammad Al-Ramahi, Izzat Alsmadi, Abdullah Wahbeh Edit "Predicting Question Quality on StackOverflow with Neural Networks"
arXiv:2404.14449v1 Announce Type: new Abstract: The wealth of information available through the Internet and social media is unprecedented. Within computing fields, websites such as Stack Overflow are considered important sources for users seeking solutions to their computing and programming issues. However, like other social media platforms, Stack Overflow contains a mixture of relevant and irrelevant information. In this paper, we evaluated neural network models to predict the quality of questions on Stack Overflow, as an example of Question Answering (QA) communities. Our results demonstrate the effectiveness of neural network models compared to baseline machine learning models, achieving an accuracy of 80%. Furthermore, our findings indicate that the number of layers in the neural network model can significantly impact its performance.

Evaluation of Machine Translation Based on Semantic Dependencies and Keywords

Kewei Yuan, Qiurong Zhao, Yang Xu, Xiao Zhang, Huansheng Ning Edit "Evaluation of Machine Translation Based on Semantic Dependencies and Keywords"
arXiv:2404.14443v1 Announce Type: new Abstract: In view of the fact that most of the existing machine translation evaluation algorithms only consider the lexical and syntactic information, but ignore the deep semantic information contained in the sentence, this paper proposes a computational method for evaluating the semantic correctness of machine translations based on reference translations and incorporating semantic dependencies and sentence keyword information. Use the language technology platform developed by the Social Computing and Information Retrieval Research Center of Harbin Institute of Technology to conduct semantic dependency analysis and keyword analysis on sentences, and obtain semantic dependency graphs, keywords, and weight information corresponding to keywords. It includes all word information with semantic dependencies in the sentence and keyword information that affects semantic information. Construct semantic association pairs including word and dependency multi-features. The key semantics of the sentence cannot be highlighted in the semantic information extracted through semantic dependence, resulting in vague semantics analysis. Therefore, the sentence keyword information is also included in the scope of machine translation semantic evaluation. To achieve a comprehensive and in-depth evaluation of the semantic correctness of sentences, the experimental results show that the accuracy of the evaluation algorithm has been improved compared with similar methods, and it can more accurately measure the semantic correctness of machine translation.

Domain Adaptation in Intent Classification Systems: A Review

Jesse Atuhurra, Hidetaka Kamigaito, Taro Watanabe, Eric Nichols Edit "Domain Adaptation in Intent Classification Systems: A Review"
arXiv:2404.14415v1 Announce Type: new Abstract: Dialogue agents, which perform specific tasks, are part of the long-term goal of NLP researchers to build intelligent agents that communicate with humans in natural language. Such systems should adapt easily from one domain to another to assist users in completing tasks. Researchers have developed a broad range of techniques, objectives, and datasets for intent classification to achieve such systems. Despite the progress in developing intent classification systems (ICS), a systematic review of the progress from a technical perspective is yet to be conducted. In effect, important implementation details of intent classification remain restricted and unclear, making it hard for natural language processing (NLP) researchers to develop new methods. To fill this gap, we review contemporary works in intent classification. Specifically, we conduct a thorough technical review of the datasets, domains, tasks, and methods needed to train the intent classification part of dialogue systems. Our structured analysis describes why intent classification is difficult and studies the limitations to domain adaptation while presenting opportunities for future work.

Characterizing LLM Abstention Behavior in Science QA with Context Perturbations

Bingbing Wen, Bill Howe, Lucy Lu Wang Edit "Characterizing LLM Abstention Behavior in Science QA with Context Perturbations"
arXiv:2404.12452v1 Announce Type: new Abstract: The correct model response in the face of uncertainty is to abstain from answering a question so as not to mislead the user. In this work, we study the ability of LLMs to abstain from answering context-dependent science questions when provided insufficient or incorrect context. We probe model sensitivity in several settings: removing gold context, replacing gold context with irrelevant context, and providing additional context beyond what is given. In experiments on four QA datasets with four LLMs, we show that performance varies greatly across models, across the type of context provided, and also by question type; in particular, many LLMs seem unable to abstain from answering boolean questions using standard QA prompts. Our analysis also highlights the unexpected impact of abstention performance on QA task accuracy. Counter-intuitively, in some settings, replacing gold context with irrelevant context or adding irrelevant context to gold context can improve abstention performance in a way that results in improvements in task performance. Our results imply that changes are needed in QA dataset design and evaluation to more effectively assess the correctness and downstream impacts of model abstention.

AmbigDocs: Reasoning across Documents on Different Entities under the Same Name

Yoonsang Lee, Xi Ye, Eunsol Choi Edit "AmbigDocs: Reasoning across Documents on Different Entities under the Same Name"
arXiv:2404.12447v1 Announce Type: new Abstract: Different entities with the same name can be difficult to distinguish. Handling confusing entity mentions is a crucial skill for language models (LMs). For example, given the question "Where was Michael Jordan educated?" and a set of documents discussing different people named Michael Jordan, can LMs distinguish entity mentions to generate a cohesive answer to the question? To test this ability, we introduce a new benchmark, AmbigDocs. By leveraging Wikipedia's disambiguation pages, we identify a set of documents, belonging to different entities who share an ambiguous name. From these documents, we generate questions containing an ambiguous name and their corresponding sets of answers. Our analysis reveals that current state-of-the-art models often yield ambiguous answers or incorrectly merge information belonging to different entities. We establish an ontology categorizing four types of incomplete answers and automatic evaluation metrics to identify such categories. We lay the foundation for future work on reasoning across multiple documents with ambiguous entities.

mOthello: When Do Cross-Lingual Representation Alignment and Cross-Lingual Transfer Emerge in Multilingual Models?

Tianze Hua, Tian Yun, Ellie Pavlick Edit "mOthello: When Do Cross-Lingual Representation Alignment and Cross-Lingual Transfer Emerge in Multilingual Models?"
arXiv:2404.12444v1 Announce Type: new Abstract: Many pretrained multilingual models exhibit cross-lingual transfer ability, which is often attributed to a learned language-neutral representation during pretraining. However, it remains unclear what factors contribute to the learning of a language-neutral representation, and whether the learned language-neutral representation suffices to facilitate cross-lingual transfer. We propose a synthetic task, Multilingual Othello (mOthello), as a testbed to delve into these two questions. We find that: (1) models trained with naive multilingual pretraining fail to learn a language-neutral representation across all input languages; (2) the introduction of "anchor tokens" (i.e., lexical items that are identical across languages) helps cross-lingual representation alignment; and (3) the learning of a language-neutral representation alone is not sufficient to facilitate cross-lingual transfer. Based on our findings, we propose a novel approach - multilingual pretraining with unified output space - that both induces the learning of language-neutral representation and facilitates cross-lingual transfer.

Advancing Social Intelligence in AI Agents: Technical Challenges and Open Questions

Leena Mathur, Paul Pu Liang, Louis-Philippe Morency Edit "Advancing Social Intelligence in AI Agents: Technical Challenges and Open Questions"
arXiv:2404.11023v1 Announce Type: new Abstract: Building socially-intelligent AI agents (Social-AI) is a multidisciplinary, multimodal research goal that involves creating agents that can sense, perceive, reason about, learn from, and respond to affect, behavior, and cognition of other agents (human or artificial). Progress towards Social-AI has accelerated in the past decade across several computing communities, including natural language processing, machine learning, robotics, human-machine interaction, computer vision, and speech. Natural language processing, in particular, has been prominent in Social-AI research, as language plays a key role in constructing the social world. In this position paper, we identify a set of underlying technical challenges and open questions for researchers across computing communities to advance Social-AI. We anchor our discussion in the context of social intelligence concepts and prior progress in Social-AI research.