Large language models (LLMs) are prone to hallucinations, which sparked a widespread effort to detect and prevent them. Recent work attempts to mitigate hallucinations by intervening in the model's generation, typically computing representative vectors of hallucinations vs. grounded generations, for steering the model's hidden states away from a hallucinatory state. However, common studies employ different setups and do not properly separate different possible causes of hallucinations, making interventions misguided. In this work, we introduce a method for categorizing examples based on the model's prior knowledge, named WACK. We construct WACK benchmarks that support interventions in two settings: open-book and closed-book question answering. Using the benchmarks, we perform an extensive investigation of the effect of different choices for intervention, such as the intervened components, and how often and how strongly to intervene. We find that intervention success varies depending on the component, with the attention blocks performing well and the residual stream proving detrimental to language modeling capabilities. We also show that interventions can benefit from representative vectors collected before, rather than after, a hallucination occurs. Finally, we introduce a new dynamic intervention, which intervenes only if needed, and thus is more robust than standard static interventions. The code is available at https://github.com/technion-cs-nlp/hallucination-mitigation .
Don't Believe Everything You Read: Enhancing Summarization Interpretability through Automatic Identification of Hallucinations in Large Language Models
Towards Detecting LLMs Hallucination via Markov Chain-based Multi-agent Debate Framework
Wangxuan Institute of Computer Technology, Peking University(北京大学王选计算机研究所);Gaoling School of Artifical Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院)
On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination Mitigation
Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences, Beijing, China(中国科学院软件研究所信息处理实验室,北京,中国);University of Chinese Academy of Sciences, Beijing, China(中国科学院大学,北京,中国);Xiaohongshu Inc(小红书公司)
Hallucinations as Orthogonal Noise: Inference-Time Manifold Alignment via Dynamic Contextual Orthogonalization
Xi’an Jiaotong University(西安交通大学);Xingchen AGI Lab(星辰AGI实验室);China Telecom AI Technology (Beijing) Co., Ltd.(中国电信人工智能技术(北京)有限公司);Institute of Artificial Intelligence, China Telecom(中国电信人工智能研究院);University of Science and Technology of China(中国科学技术大学);Tsinghua University(清华大学)
Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shifting
Faculty of Information Technology, Monash University(墨尔本大学信息科技学院);Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center, Qilu University of Technology (Shandong Academy of Sciences)(教育部计算能力网络与信息安全重点实验室,山东计算机科学中心,齐鲁大学(山东科学院));Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science(山东省计算能力互联网与服务计算重点实验室,山东省计算机科学基础研究中心);School of Computer Science and Technology, Anhui University(安徽大学计算机科学与技术学院)
TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space
Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);Key Laboratory of AI Safety, Chinese Academy of Sciences(中国科学院人工智能安全重点实验室)
Intelligent Identification and Repair of Design Defects in BIM via Domain-Specific Large Language Models
Tsinghua University(清华大学);Key Laboratory of Digital Construction and Digital Twin, Ministry of Housing and Urban-Rural Development(住房和城乡建设部数字建造与数字孪生重点实验室);PetroChina Planning & Engineering Institute(中国石油规划总院)
Tuning-Free Accountable Intervention for LLM Deployment -- A Metacognitive Approach
Arizona State University(亚利桑那州立大学);University of Science and Technology of China(中国科学技术大学);University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校);MIT(麻省理工学院);Harvard University(哈佛大学)
ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models
Tsinghua University(清华大学);Zhipu AI(智谱AI);Chongqing University(重庆大学);Shanghai Jiao Tong University(上海交通大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination Via Latent Truthful-Guided Pre-Intervention
Drexel University(德雷塞尔大学);University of Electronic Science and Technology of China(电子科技大学);Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州));LLNL(劳伦斯利弗莫尔国家实验室);Lehigh University(莱斯大学)
Steering LVLMs via Sparse Autoencoder for Hallucination Mitigation
School of Computer Science and Engineering, Southeast University(东南大学计算机科学与工程学院);Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University)(东南大学新一代人工智能技术及其交叉应用关键实验室);Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所基础模型研究中心);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);Department of Computer Science and Technology, Tsinghua University(清华大学计算机科学与技术系);Wuhan University of Technology(武汉理工大学);National University of Singapore(新加坡国立大学)
ClinHallu: A Benchmark for Diagnosing Stage-Wise Hallucinations in Medical MLLM Reasoning
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));DAMO Academy, Alibaba Group(阿里巴巴达摩院);Hupan Lab(湖畔实验室);Zhejiang University(浙江大学)