Language models often answer with high confidence, as measured by output entropy, even when they are wrong. We study two situations that lead to such errors, knowledge conflict, where the context contradicts a fact stored in the weights and the two sources interfere, and missing knowledge, where the fact was never learned and the model hallucinates. To control what the model knows, we fine-tune it on synthetic facts that map arbitrary entity identifiers to random codes, installed through LoRA adapters on the MLP, query-key (QK), or value-output (VO) components of the transformer. Our analysis suggests that MLP is the main substrate for storing facts in basins, regions where a fact's representations converge, while QK steers generation toward a basin or the context, and VO writes the retrieved content into the residual stream. Under knowledge conflict, the form of interference depends on how the fact is learned. A fact learned from a single phrasing yields to the context, with each adapter leaving an error pattern consistent with its circuit role. A fact learned from many phrasings overrides the context, and under contradiction the answer starts on the stored code and drifts away from it. Under missing knowledge, the hidden state reaches no basin, yet every adapter placement produces confident hallucinations, VO most of all. In both situations, output entropy reflects how sharply the model commits rather than whether the answer is correct, even though the model's representations still separate correct answers from errors. Across 12 pretrained models, the hallucination rate falls with scale, but a growing fraction of the remaining hallucinations are confident. In the models we study, the gap between confidence and correctness does not close with scale, and flagging these errors requires confidence that reflects where the answer comes from, rather than how sharply the model commits to it.
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)
HalluClear: Diagnosing, Evaluating and Mitigating Hallucinations in GUI Agents
MAIS&NLPR, Institute of Automation, Chinese Academy of Sciences(自动化研究所人工智能与自然语言处理实验室,中国科学院);School of Artificial Intelligence, UCAS(中国科学院大学人工智能学院);Meituan(美团)
Hallucination in Medical Imaging AI: A Cross-Modality Analytical Framework for Taxonomy, Detection, and Mitigation under Regulatory Constraints
King Fahd University of Petroleum & Minerals, Saudi Arabia(沙特阿拉伯法赫德国王石油矿产大学);SDAIA-KFUPM Joint Research Center for Artificial Intelligence, Saudi Arabia(沙特阿拉伯SDAIA-KFUPM人工智能联合研究中心)
Before the Token Commits: Trajectory-Level Benchmarking of Visual Hallucinations in Diffusion VLMs
Nanjing University of Aeronautics and Astronautics(南京航空航天大学);State Key Laboratory of Ocean Sensing, ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University(浙江大学杭州国际科创中心海洋感知全国重点实验室);Security Capability Center(360安全能力中心)
Hallucination Across the Reasoning Lifecycle: Interface Visibility, Causal Evidence, and Release Control in Large Reasoning Models
Zhejiang University(浙江大学);Binjiang Institute of Zhejiang University(浙江大学滨江研究院);Guangzhou University(广州大学);Rensselaer Polytechnic Institute(伦斯勒理工学院);The University of Hong Kong(香港大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));The Hong Kong Polytechnic University(香港理工大学);Zhejiang Lab(之江实验室)
AI Slop and Hallucinations in Vulnerability Assessment: A Survey on Reasoning Failures and Trustworthy Mitigation
University of New South Wales(新南威尔士大学);University of Wollongong(伍伦贡大学);Nanjing University of Information Science & Technology(南京信息工程大学);Griffith University(格里菲斯大学);Nanyang Technological University(南洋理工大学)
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)
Center for Foundation Models and Generative AI, Northwestern University(基础模型与生成式人工智能中心,西北大学);Department of Computer Science, Northwestern University(计算机科学系,西北大学);Ensemble AI;Engineering Science, University of Toronto(工程科学,多伦多大学);University of California, Berkeley(加州大学伯克利分校);Department of Statistics and Data Science, Northwestern University(统计与数据科学系,西北大学)
BenHalluEval: A Multi-Task Hallucination Evaluation Framework for Large Language Models on Bengali
Department of Computer Science and Engineering, Islamic University of Technology(伊斯兰科技大学计算机科学与工程系);Department of Computer Science and Engineering, University of California(加州大学计算机科学与工程系)
Do LLM hallucination detectors suffer from low-resource effect?
Indian Institute of Technology Kharagpur(印度理工学院卡拉格普尔分校);Ruhr University Bochum(波鸿鲁尔大学);UAR Research Center for Trustworthy Data Science and Security(UAR可信数据科学与安全研究中心)
Beyond "Hallucinations": A Framework for Stable Human-AI Reasoning
Faculty of Medicine, Lund University(隆德大学医学院);Department of Economics, Lund University School of Economics and Management(隆德大学经济学与管理学院经济系);Department of Health Services Research and Policy, London School of Hygiene & Tropical Medicine(伦敦大学卫生与热带医学学院健康服务研究与政策系)