Large language models are successful in answering factoid questions but are also prone to hallucination. We investigate the phenomenon of LLMs possessing correct answer knowledge yet still hallucinating from the perspective of inference dynamics, an area not previously covered in studies on hallucinations. We are able to conduct this analysis via two key ideas. First, we identify the factual questions that query the same triplet knowledge but result in different answers. The difference between the model behaviors on the correct and incorrect outputs hence suggests the patterns when hallucinations happen. Second, to measure the pattern, we utilize mappings from the residual streams to vocabulary space. We reveal the different dynamics of the output token probabilities along the depths of layers between the correct and hallucinated cases. In hallucinated cases, the output token's information rarely demonstrates abrupt increases and consistent superiority in the later stages of the model. Leveraging the dynamic curve as a feature, we build a classifier capable of accurately detecting hallucinatory predictions with an 88\% success rate. Our study shed light on understanding the reasons for LLMs' hallucinations on their known facts, and more importantly, on accurately predicting when they are hallucinating.
DHI: Leveraging Diverse Hallucination Induction for Enhanced Contrastive Factuality Control in Large Language Models
School of Computer Science, Wuhan University（武汉大学计算机学院）；Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院）
AutoHall: Automated Factuality Hallucination Dataset Generation for Large Language Models
AGI Institute, School of Computer Science, Shanghai Jiao Tong University（AGI研究院，计算机科学学院，上海交通大学）；Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3（上海可信数据流通与治理Web3重点实验室）；School of Media & Communication, Shanghai Jiao Tong University（媒体与传播学院，上海交通大学）
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）
Mitigating Geospatial Knowledge Hallucination in Large Language Models: Benchmarking and Dynamic Factuality Aligning
College of AI, Tsinghua University（清华大学人工智能学院）；Department of Electronic Engineering, BNRist, Tsinghua University（清华大学电子工程系）；School of Electronic and Information Engineering, Beijing Jiaotong University（北京交通大学电子信息学院）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）
Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-based Retrofitting
Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；State Key Laboratory of Computer Science（计算机科学国家重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）
Detecting LLM Fact-conflicting Hallucinations Enhanced by Temporal-logic-based Reasoning
Huazhong University of Science and Technology（华中科技大学）；National University of Singapore（新加坡国立大学）；University of New South Wales（新南威尔士大学）；Nanyang Technological University（南洋理工大学）
Why Fine-Tuning Encourages Hallucinations and How to Fix It
Hebrew University of Jerusalem（海法大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Technion – Israel Institute of Technology（技术学院 – 以色列理工学院）；University of Southern California（南加州大学）
The Hallucinations Leaderboard -- An Open Effort to Measure Hallucinations in Large Language Models
School of Informatics, University of Edinburgh（爱丁堡大学信息学院）；School of Electronics Engineering and Computer Science, Peking University（北京大学电子工程与计算机科学学院）；Hugging Face；Department of Computer Science, University College London（伦敦大学学院计算机系）；Together AI
Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Models
Department of Computer Science and Engineering, United International University, Dhaka 1212, Bangladesh（乌姆特国际大学计算机科学与工程系）；Department of Computer Science and Engineering, Daffodil International University, Dhaka-1341, Bangladesh（达芙尼国际大学计算机科学与工程系）；Faculty of Science and Technology, Charles Darwin University, Casuarina, NT 0909, Australia（查尔斯·达尔文大学科学与技术学院）
Hallucinations in Large Multilingual Translation Models
Instituto de Telecomunicações（电信研究所）；Instituto Superior Técnico, University of Lisbon（里斯本大学高等技术学院）；University of Edinburgh（爱丁堡大学）；CentraleSupélec, Université Paris-Saclay（巴黎萨克雷大学中央理工-高等电力学院）；Unbabel（Unbabel公司）
Retrieval, not hallucinations, will be the limiting factor for LLM-based clinical AI tools
The University of Texas Health Science Center at Houston（德克萨斯大学休斯顿健康科学中心）；Oregon Health & Science University（俄勒冈健康与科学大学）；Mayo Clinic（梅奥诊所）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）
Exploring the Generalizability of Factual Hallucination Mitigation via Enhancing Precise Knowledge Utilization
Dept. of Comp. Sci. and Tech.（计算机科学与技术系）；Institute for AI（人工智能研究院）；Tsinghua-Bosch Joint ML Center（清华大学-博世联合机器学习中心）；THBI Lab（THBI实验室）；BNRist Center（BNRist中心）；Tsinghua University（清华大学）
