大语言模型(LLM)在各类自然语言处理(NLP)任务中表现出色,但在模糊语境下容易生成不可靠的推测内容,即幻觉。本文提出一种基于不可解数学应用题(MWP)评估问答(QA)场景下LLM幻觉的新方法。为支撑该方法,我们创新性构建了名为Unanswerable Math Word Problem(UMWP,不可解数学应用题)的数据集,包含5大类共5200道题目。我们开发了结合文本相似度与数学表达式检测的评估方法,以判定LLM是否认为题目不可解。对GPT-3、InstructGPT、LLaMA、Claude等31个LLM开展的大量实验结果表明,上下文学习与基于人类反馈的强化学习(RLHF)训练能显著提升模型避免幻觉的能力。研究证明,利用数学应用题是评估幻觉的可靠有效方法。我们的代码与数据可在https://github.com/Yuki-Asuuna/UMWP获取。
英文摘要:
Large language models (LLMs) are highly effective in various natural language processing (NLP) tasks. However, they are susceptible to producing unreliable conjectures in ambiguous contexts called hallucination. This paper presents a new method for evaluating LLM hallucination in Question Answering (QA) based on the unanswerable math word problem (MWP). To support this approach, we innovatively develop a dataset called Unanswerable Math Word Problem (UMWP) which comprises 5200 questions across five categories. We developed an evaluation methodology combining text similarity and mathematical expression detection to determine whether LLM considers the question unanswerable. The results of extensive experiments conducted on 31 LLMs, including GPT-3, InstructGPT, LLaMA, and Claude, demonstrate that in-context learning and reinforcement learning with human feedback (RLHF) training significantly enhance the model's ability to avoid hallucination. We show that utilizing MWP is a reliable and effective approach to assess hallucination. Our code and data are available at https://github.com/Yuki-Asuuna/UMWP.
Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Models
Graduate Institute of Communication Engineering, National Taiwan University, Taiwan(台湾大学通讯工程研究所);Artificial Intelligence Center of Research Excellence (AI-CoRE), National Taiwan University, Taiwan(台湾大学人工智能卓越研究中心)
TUBench: Benchmarking Large Vision-Language Models on Trustworthiness with Unanswerable Questions
The University of Hong Kong(香港大学);Xi’an Jiaotong-Liverpool University(西交利物浦大学);School of Computer Science and Engineering, Beihang University(北京航空航天大学计算机学院);Zhongguancun Laboratory(中关村实验室)
AURORA: Asymmetry and Update-Induced Rotation for Robust Hallucination Detection in Large Language Models
School of Artificial Intelligence, Beihang University, China(北京航空航天大学人工智能学院);Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University, China(北京航空航天大学未来区块链与隐私计算先进创新中心)
Small Agent Can Also Rock! Empowering Small Language Models as Hallucination Detector
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院);DIRO, Université de Montréal(蒙特利尔大学 DIRO 学院);Kuaishou(快手);School of Information, Renmin University of China(中国人民大学信息学院)
SelfCheck-Eval: A Multi-Module Framework for Zero-Resource Hallucination Detection in Large Language Models
Department of Mathematics and Computer Science, University of Catania(卡塔尼亚大学数学与计算机科学系);L3S Research Center, Leibniz University Hannover(汉诺威莱布尼茨大学L3S研究中心)
Utilize the Flow before Stepping into the Same River Twice: Certainty Represented Knowledge Flow for Refusal-Aware Instruction Tuning
Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Peking University(北京大学);Southwest Jiaotong University(西南交通大学);Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences(中国科学院大学杭州高等研究院)
Expanding before Inferring: Enhancing Factuality in Large Language Models through Premature Layers Interpolation
Sun Yat-Sen University(中山大学);Shenzhen MSU-BIT University(深圳MSU-BIT大学);The Hong Kong Polytechnic University(香港理工大学);UNSW, Sydney, NSW 2052, Australia(新南威尔士大学);Shenzhen Key Laboratory for High Performance Data Mining, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(深圳高性能数据挖掘重点实验室,深圳先进技术研究院,中国科学院)
Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification
School of Computer Science, National Key Laboratory for Multimedia Information Processing, PKU-Anker LLM Lab, Peking University(计算机学院、多媒体信息处理国家重点实验室、PKU-Anker LLM实验室、北京大学);Huawei Noah’s Ark Lab(华为诺亚实验室);The Hong Kong University of Science and Technology(香港科技大学);The Hong Kong Polytechnic University(香港理工大学)