Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration
University of Washington(华盛顿大学);University of California, Berkeley(加州大学伯克利分校);The Hong Kong University of Science and Technology(香港科技大学);Carnegie Mellon University(卡内基梅隆大学)
Despite efforts to expand the knowledge of large language models (LLMs), knowledge gaps -- missing or outdated information in LLMs -- might always persist given the evolving nature of knowledge. In this work, we study approaches to identify LLM knowledge gaps and abstain from answering questions when knowledge gaps are present. We first adapt existing approaches to model calibration or adaptation through fine-tuning/prompting and analyze their ability to abstain from generating low-confidence outputs. Motivated by their failures in self-reflection and over-reliance on held-out sets, we propose two novel approaches that are based on model collaboration, i.e., LLMs probing other LLMs for knowledge gaps, either cooperatively or competitively. Extensive experiments with three LLMs on four QA tasks featuring diverse knowledge domains demonstrate that both cooperative and competitive approaches to unveiling LLM knowledge gaps achieve up to 19.3% improvements on abstain accuracy against the strongest baseline. Further analysis reveals that our proposed mechanisms could help identify failure cases in retrieval augmentation and pinpoint knowledge gaps in multi-hop reasoning.
Don't Believe Everything You Read: Enhancing Summarization Interpretability through Automatic Identification of Hallucinations in Large Language Models
Beyond "I Don't Know": Evaluating LLM Self-Awareness in Discriminating Data and Model Uncertainty
Dept. of Comp. Sci. & Tech., Institute for AI, Tsinghua University, Beijing, China(计算机科学与技术系,人工智能研究院,清华大学,北京,中国);Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China(人工智能产业研究院(AIR),清华大学,北京,中国)
CLEAR: Revealing How Noise and Ambiguity Degrade Reliability in LLMs for Medicine
Department of Biomedical Informatics, Vanderbilt University Medical Center(生物医学信息学系,范德比尔特大学医学中心);Vanderbilt University(范德比尔特大学);Intuit AI Research(Intuit AI研究);Department of Electrical and Computer Engineering, Vanderbilt University(电气与计算机工程系,范德比尔特大学);Department of Computer Science, Vanderbilt University(计算机科学系,范德比尔特大学);Department of Biostatistics, Vanderbilt University Medical Center(生物统计学系,范德比尔特大学医学中心)
Faithful Activation Verbalization: Reducing Hallucinations in LLM Representation Interpretation
New Jersey Institute of Technology(新泽西理工学院);Shanghai AI Laboratory(上海人工智能实验室);Xi’an JiaoTong University(西安交通大学);Chinese Univerity of Hongkong, Shenzhen(香港中文大学(深圳))
The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models
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(蒙特利尔大学计算机科学与运筹学系);School of Information, Renmin University of China(中国人民大学信息资源管理学院)