LLM Hallucination Mitigation

LLM: Large Language Model

The field studies how to make language-model answers more faithful to evidence and more honest about uncertainty. Common approaches include retrieval-augmented generation with claim-level verification, knowledge graphs and structured tools, fine-tuning or reinforcement learning, decoding and activation interventions, and calibrated abstention. Evaluation spans factual question answering, long-form summaries, retrieval-augmented systems, high-stakes medical and legal tasks, vision-language models, and tool-using agents. A central tension is reducing unsupported claims without causing excessive refusal, losing useful information, degrading general capabilities, or adding prohibitive cost and latency.

Latest papers

180 papers13 papers in the last four weeks, down 7% on the four weeks before. 0.1% of all new papers.

What Hallucinations Have We Measured? Semantic Illusion, Confabulation, and Expressed Uncertainty
Oct 28, 2026Hazel H. Kim, Jakub Binkowski, Ekaterina Fadeeva +22Hallucination in Language Models LLM Hallucination Detection
University of Oxford · Wroclaw University of Science and Technology · ETH Zurich +14
CANS: Capability-Preserving Neuron Steering for Large Language Models
Oct 26, 2026Yucheng Wu, Chengyi Xie, Chenpeng Wang +1Language Model Steering Safety-Utility Trade-Off in Language Models
State Key Laboratory of Multimedia Information Processing, Peking University · School of Computer Science, Peking University · YiXin-AILab, YIXIN, Beijing, China
Tracing Hallucinations in LLM Reasoning for UML Class Diagram Generation: An Empirical Taxonomy and Mitigation Study
Oct 22, 2026Mojdeh Rahmanian, Foutse Khomh, Ashkan Sami +1Hallucination in Language Models LLM Hallucination Mitigation
Edinburgh Napier University, Edinburgh, Scotland · Polytechnique Montréal, Montréal, QC, Canada
Conflicted Records: Typed Adversarial Contracts for Auditable LLM Output Quality Enforcement
Oct 21, 2026Kardelen Subasi, Jarosław A. ChudziakLLM Auditing LLM Hallucination Mitigation
Warsaw University of Technology, Warsaw, Poland
Omni-Woodpecker: Hallucination Correction via Evidence-Prior Rebalancing for Omni LLMs
Oct 19, 2026Zijian Liu, Chaoyou Fu, Yan Yang +2LLM Hallucination Mitigation Multimodal Hallucination
School of Intelligence Science and Technology, Nanjing University, Suzhou 215163, China. · University of Chinese Academy of Sciences, Beijing 100049, China.
Strong yet Controllable LLM Abstention without Learning to Abstain
Oct 12, 2026Junwei Zhang, Yifei Wang, Wanli Yang +6Factual QA LLM Abstention
State Key Laboratory of AI Safety, Institute of Computing Technology, CAS · University of Chinese Academy of Sciences · Beijing Institute of Technology
Phantom Merge: When Your Large Language Model Agents Pick One but Tell You About Another
Oct 12, 2026Wangshu Zhu, Qianwen Guo, Yushun DongLLM Grounding LLM Agent Reliability
Department of Computer Science, Florida State University · Department of Civil and Environmental Engineering, FAMU–FSU College of Engineering
Tracing and Taming Hallucinated Terms via Subsequence-Association Filtering and Breadth-Aware Selection for LLM Query Expansion
Oct 9, 2026Amit Kumar Jaiswal, Sagar Uprety, Prayag TiwariQuery Expansion Information Retrieval
Indian Institute of Technology (BHU), Varanasi, India · University College London, London, UK · Halmstad University, Halmstad, Sweden
PHRBench: A Behavioral Evaluation of Post-Hallucination Reasoning in LLMs
Oct 7, 2026Linghao Meng, Feng He, Xuan Yang +5Hallucination in Language Models LLM Hallucination Mitigation
National University of Singapore · Independent Researcher · Tsinghua University +2
Hallucination Across the Reasoning Lifecycle: Interface Visibility, Causal Evidence, and Release Control in Large Reasoning Models
Oct 4, 2026Zhe Yu, Mohan Li, Lei Yu +6LLM Hallucination Mitigation Hallucination in Language Models
Zhejiang University, China · Binjiang Institute of Zhejiang University, China · Guangzhou University, China +5
Invisible Ink, Visible Lies: How Production Watermarking Causes LLMs to Hallucinate
Oct 4, 2026Haocheng Ye, Aoting Hu, Xinwei Zhang +3Text Watermarking LLM Watermarking
Nanjing University of Science and Technology · Anhui University of Technology · The Hong Kong Polytechnic University +2
Understanding and Mitigating Hallucination Escape in Tool-Using LLM Agents
Oct 3, 2026Peigui Qi, Kunsheng Tang, Yide Song +2LLM Hallucination Mitigation LLM Tool Use
University of Science and Technology of China · University of Washington
HARPO: Hallucination-Aware Reinforcement Learning for Faithful and Creative Language Generation
Oct 2, 2026Tiezheng Yu, Yuxin Jiang, Jinpeng Li +4LLM Hallucination Mitigation Text Generation
Huawei Technologies
Alleviating Hallucination in Reasoning Tasks with Training-Free Uncertainty-Guided Steering
Sep 30, 2026Litian Liu, Qiqi Hou, Yubing Jian +5LLM Hallucination Mitigation Activation Steering
Qualcomm AI Research · UC Santa Barbara
Devils in Question Relay: Source-Conditioned Relay Steering to Mitigate Hallucinations in Audio-visual Large Language Models
Sep 29, 2026Yu Zhang, Pingrui Zhang, Xuefeng Bai +3LLM Hallucination Mitigation Hallucination in Language Models
Harbin Institute of Technology, Shenzhen, China
Conformal Factuality Control for Multi-Hop Retrieval-Augmented Generation
Sep 27, 2026Muhammad Aimal Rehman, Chi-Kuang YehRetrieval-Augmented Generation LLM Hallucination Mitigation
Department of Mathematics & Statistics Georgia State University Atlanta, GA, USA
Faithful Activation Verbalization: Reducing Hallucinations in LLM Representation Interpretation
Sep 27, 2026Haiyan Zhao, Zirui Hei, Wei Shi +3LLM Hallucination Mitigation LLM Interpretability
New Jersey Institute of Technology · Shanghai AI Laboratory · Xi’an JiaoTong University +1
Tutoring Large Language Models to be Domain-adaptive, Precise and Safe
Sep 19, 2026Somnath BanerjeeLLM Safety LLM Safety Alignment
Enforcing Narrative Reliability and Epistemic Pacing in LLM-Driven Detective Games via Structured Knowledge Trees
Sep 19, 2026Parsa Rahmati, Richard ZhaoInteractive Storytelling Conversational Agents
Department of Computer Science, University of Calgary Calgary, Alberta, Canada, T2N 1N4
An Interpretable Memory Decision Controller for LLM Agents Based on Three-Signal Complementarity: Decoupling Confidence and Consistency
Sep 18, 2026Yiming Zhang, Jinghong Zhang, Haoran Zhao +2Memory-Augmented Language Models LLM Hallucination Mitigation
School of Computer Science and Engineering, Tianjin University of Technology Tianjin, China
SAGE: Governed Artifact Generation from Enterprise Guidelines
Sep 15, 2026Mohammadreza Sediqin, Shivali Dalmia, Sumukha Thoppanahalli +2LLM Hallucination Mitigation LLM Guardrails
Centific Research New York, USA · Centific Research Seattle, USA · Centific Research Washington, USA
Look Before You Leap: Factual Decoding with Internal Attribution Signals
Sep 14, 2026Hayeong Ryu, JungMin Yun, Byeonggeuk Lim +2Language Model Decoding Language Model Error Detection
Department of Artificial Intelligence, Chung-Ang University · Graduate School of Advanced Imaging Sciences, Multimedia and Film, Chung-Ang University
Route, Don't Fix: Regime-Dependent Decoding Correction and a Trajectory-Gated Router for Reliable Clinical LLM Answer Selection
Sep 13, 2026Zeyu Dong, Benjamin Wang, Joyee W. JinAdaptive Inference Language Model Decoding
St. Theresa of Lisieux Catholic High School Toronto, Canada · Department of Computer Science University of Toronto Toronto, Canada
Domain-Specific Hallucination Detection in Large Language Models
Sep 10, 2026Varun Teja Chundru, Debasmita BiswasLanguage Model Error Detection LLM Hallucination Mitigation
Department of Computer Science Purdue University Fort Wayne
Noēsis: Deterministic-First Retrieval with Two-Tier Context Hydration for Factuality-Critical Queries on Small Local Models
Sep 7, 2026Nicola CogottiRetrieval-Augmented Generation LLM Grounding
Alpha Cogs
GRACE: Graph-Grounded Reflective Agent Copilot Engine for Expert-in-the-Loop Knowledge Expansion
Sep 3, 2026John Seon Keun Yi, Joshua R. Minot, Dokyun LeeLLM Grounding LLM Hallucination Mitigation
Boston University · MassMutual
SFAD: Speculative Factuality-Aware Decoding
Sep 1, 2026Guanqiao Chen, Di Wang, Lijie HuLLM Hallucination Mitigation Speculative Decoding
1MBZUAI · University of Science and Technology of China · 3Provable Responsible AI and Data Analytics (PRADA) Lab +1
Stick to What You Know: A Study of Knowledge-Aligned Supervised Fine-Tuning
Aug 31, 2026Arthur Becker, Jakob Kemmler, David Thulke +3Supervised Fine-Tuning LLM Hallucination Mitigation
AppTek GmbH, Aachen, Germany · Machine Learning and Human Language Technology, RWTH Aachen University, Germany
MedAgent-R1: Faithfulness-Aware Reinforcement Learning for Evidence-Grounded Medical Reasoning
Aug 31, 2026Jiangwang Chen, Chenghao Zhang, Hengxing CaiLLM Hallucination Mitigation Evidence-Grounded Reasoning
Tsinghua University · DP Technology
Compression-Aware Abstention: Teaching LLMs to Refuse When KV-Compression Masks Remove Answer Evidence
Aug 30, 2026Mohammadali Khodabandehlou, Bhaskar KrishnamachariLLM Hallucination Mitigation KV Caching
University of Southern California

Oct 28, 2026J/K move · Enter open · S save

What Hallucinations Have We Measured? Semantic Illusion, Confabulation, and Expressed Uncertainty

Hazel H. Kim, Jakub Binkowski, Ekaterina Fadeeva, Juan David Guerra+21

University of Oxford · Wroclaw University of Science and Technology · ETH Zurich+14

Hallucination in Language Models LLM Hallucination Detection LLM Hallucination Mitigation LLM Uncertainty Estimation

Open paper AskPDF arXiv

Hallucination remains one of the most critical challenges in deploying large language models (LLMs) reliably and safely. Yet the term is used inconsistently across the research community. We argue for a strict definition of hallucinations in LLMs. First, hallucinations should be confident incorrectness, kept separate from expressed uncertainty (UNK)1. UNK reveals that the model may be wrong, whereas a hallucination does not reveal it and is therefore more dangerous in practice. Conflating the two obscures their distinct behaviors and makes them hard to study. Second, hallucinations should be split by a simple re-elicitation test: does any semantically equivalent prompt recover the correct response? This test probes whether the relevant knowledge2 is accessible. If none does, the knowledge is likely absent or inaccessible, and the error type is a confabulation (CF) that likely requires external knowledge or retraining; if some does, the knowledge is accessible from the model but applied inconsistently, and the error type is a semantic illusion (SI) that simple prompt or decoding changes can mitigate3. Re-evaluating 14 recent hallucination methods under this taxonomy yields three findings. (1) Detection methods flag UNK more often than hallucinated responses (i.e., SI and CF). (2) Mitigation methods are far more effective for SI than for CF. (3) Latent signals are more informative than output-level signals for CF. An audit of recent hallucination papers shows that most conflate these categories. We recommend reporting CF, SI, and UNK separately, and introduce a practical labeling protocol that needs only a modest number of semantically equivalent prompts.