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.

Neural Uncertainty Principle: A Unified View of Adversarial Fragility and LLM Hallucination
Mar 20, 2026Dong-Xiao Zhang, Hu Lou, Jun-Jie Zhang +2Hallucination in Language Models Adversarial Robustness
Northwest Institute of Nuclear Technology, Xi’an, Shaanxi 710024, China. · Department of Computer Science and Technology, Institute for AI, BNRist Center, THBI Lab, Tsinghua-Bosch Joint Center for ML, Tsinghua University, Beijing 10084, China · the School of Mathematics and Statistics and the Ministry of Education Key Lab of Intelligent Networks and Network Security, Xi’an Jiaotong University, Xi’an, Shaanxi 710049, China.
EvidenceRL: Reinforcing Evidence Consistency for Trustworthy Language Models
Mar 20, 2026J. Ben Tamo, Yuxing Lu, Benoit L. Marteau +2LLM Hallucination Mitigation LLM Grounding
Georgia Institute of Technology · Pekin University
Mitigating LLM Hallucinations through Domain-Grounded Tiered Retrieval
Mar 18, 2026Md. Asraful Haque, Aasar Mehdi, Maaz Mahboob +1LLM Hallucination Mitigation LLM Grounding
Computational Unit, Z.H. College of Engineering & Technology, Aligarh Muslim University, India · Interdisciplinary Center for Artificial Intelligence, Aligarh Muslim University, India · Department of Computer Engineering, Aligarh Muslim University, India
Inducing Epistemological Humility in Large Language Models: A Targeted SFT Approach to Reducing Hallucination
Mar 18, 2026Cem Uluoglakci, Tugba Taskaya TemizelLLM Hallucination Mitigation Hallucination in Language Models
Information Systems Middle East Technical University Ankara, Turkey · Data Informatics Middle East Technical University Ankara, Turkey
POaaS: Minimal-Edit Prompt Optimization as a Service to Lift Accuracy and Cut Hallucinations on On-Device sLLMs
Mar 17, 2026Jungwoo Shim, Dae Won Kim, Sun Wook Kim +4Automatic Prompt Optimization LLM Hallucination Mitigation
Electronics and Telecommunications Research Institute, Republic of Korea
An Industrial-Scale Insurance LLM Achieving Verifiable Domain Mastery and Hallucination Control without Competence Trade-offs
Mar 15, 2026Qian Zhu, Xinnan Guo, Jingjing Huo +5Domain Adaptation for LLMs LLM Alignment
Ant Group
ESG-Bench: Benchmarking Long-Context ESG Reports for Hallucination Mitigation
Mar 13, 2026Siqi Sun, Ben Peng Wu, Mali Jin +3LLM Hallucination Mitigation LLM Safety Benchmarks
School of Computer Science, University of Sheffield, Sheffield, UK
Hallucination as output-boundary misclassification: a composite abstention architecture for language models
Mar 12, 2026Angelina HintsanenLLM Hallucination Mitigation Hallucination in Language Models
NEXUS Laboratory, Helsinki, Finland
Adaptive Activation Cancellation for Hallucination Mitigation in Large Language Models
Mar 10, 2026Eric Yocam, Varghese Vaidyan, Gurcan Comert +3LLM Hallucination Mitigation Activation Steering
The Beacom College of Computer and Cyber Sciences, Dakota State University, Madison, SD 57042, USA. · Department of Computational Data Science and Engineering, North Carolina A&T State University, Greensboro, NC 27411, USA. · Department of Computer Science and Software Engineering, California Polytechnic State University, San Luis Obispo, CA 93407, USA. +2
Toward Epistemic Stability: Engineering Consistent Procedures for Industrial LLM Hallucination Reduction
Mar 8, 2026Brian Freeman, Adam Kicklighter, Matt Erdman +1LLM Hallucination Mitigation LLM Prompting
Trane Technologies, Davidson NC, USA
A Novel Multi-Agent Architecture to Reduce Hallucinations of Large Language Models in Multi-Step Structural Modeling
Mar 8, 2026Ziheng Geng, Jiachen Liu, Ran Cao +3Structural Engineering Multi-Agent LLM Systems
Department of Civil and Architectural Engineering, University of Miami, Coral Gables, FL 33146, USA · HBC Engineering Company, Miami, FL 33178, USA · College of Civil Engineering, Hunan University, Changsha, 410082, China +3
RADIANT-LLM: an Agentic Retrieval Augmented Generation Framework for Reliable Decision Support in Safety-Critical Nuclear Engineering
Mar 4, 2026Zavier Ndum Ndum, Jian Tao, John Ford +2Agentic RAG Multimodal RAG
Department of Nuclear Engineering, Texas A&M University, College Station, TX, USA · College of Performance, Visualization and Fine Arts, Texas A&M University, College Station, TX, USA
Towards Faithful Industrial RAG: A Reinforced Co-adaptation Framework for Advertising QA
Feb 26, 2026Wenwei Li, Ming Xu, Tianle Xia +7Question Answering Retrieval-Augmented Generation
Tencent
No One Size Fits All: QueryBandits for Hallucination Mitigation
Feb 23, 2026Nicole Cho, William Watson, Alec Koppel +2LLM Hallucination Mitigation Query Reformulation
JPMorgan AI Research, New York, NY, USA
AgenticSum: An Agentic Inference-Time Framework for Faithful Clinical Text Summarization
Feb 23, 2026Fahmida Liza Piya, Rahmatollah BeheshtiText Summarization LLM Hallucination Mitigation
University of Delaware, Newark, DE, USA
Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study
Feb 19, 2026Dylan Bouchard, Mohit Singh Chauhan, Viren Bajaj +1LLM Hallucination Mitigation Hallucination in Language Models
CVS Health, Wellesley, MA
Fine-Refine: Iterative Fine-grained Refinement for Mitigating Dialogue Hallucination
Feb 17, 2026Xiangyan Chen, Yujian Gan, Matthew PurverLLM Hallucination Mitigation Hallucination Mitigation
Queen Mary University of London, UK · Queen’s University Belfast, UK · Institut Jožef Stefan, Slovenia
FloCA: Towards Faithful and Logically Consistent Flowchart Reasoning
Feb 15, 2026Jinzi Zou, Bolin Wang, Shuo Zhang +2LLM Hallucination Mitigation Conversational Agents
MoE KLINNS Lab, Xi’an Jiaotong University, Xi’an 710049, P. R. China · China Mobile Group Shaanxi Co., Ltd.
Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance
Jan 20, 2026Qianli Ma, Chang Guo, Zhiheng Tian +4Multi-Agent LLM Systems LLM Hallucination Mitigation
AutoLab, School of Artificial Intelligence, Shanghai Jiao Tong University
Not All Needles Are Found: How Fact Distribution and Don't Make It Up Prompts Shape Retrieval, Reasoning, and Hallucination in Long-Context LLMs
Jan 5, 2026Amirali Ebrahimzadeh, Seyyed M. SaliliLong-Context Retrieval LLM Hallucination Mitigation
Department of Electrical Engineering & Computer Science, University of Michigan, Ann Arbor, MI 48109, USA · Independent Researcher, Ann Arbor, MI 48106, USA
Honesty over Accuracy: Trustworthy Language Models through Reinforced Hesitation
Nov 14, 2025Mohamad Amin Mohamadi, Tianhao Wang, Zhiyuan LiLLM Abstention LLM Hallucination Mitigation
Toyota Technological Institute at Chicago · University of California, San Diego
Mitigating Hallucination in Large Language Models: A Capability-Oriented Survey on RAG, Reasoning, and Agentic Systems
Oct 28, 2025Yihan Li, Xiyuan Fu, Ghanshyam Verma +2Retrieval-Augmented Generation LLM Hallucination Mitigation
Electronic Information School, Wuhan University, Wuhan, China · School of Computing, Dublin City University, Dublin, Ireland · School of Public Health, Wuhan University, Wuhan, China +2
Expert-guided Clinical Text Augmentation via Query-Based Model Collaboration
Sep 25, 2025Dongkyu Cho, Miao Zhang, Rumi ChunaraSynthetic Data Augmentation Data Augmentation
Department of Computer Science, New York University, New York, NY, United States · Department of Biostatistics, School of Global Public Health, New York University, New York, NY, United States
Geometric Uncertainty for Detecting and Correcting Hallucinations in LLMs
Sep 17, 2025Edward Phillips, Sean Wu, Soheila Molaei +3Uncertainty Quantification LLM Hallucination Mitigation
Department of Engineering Science, University of Oxford · GlaxoSmithKline · Oxford Suzhou Centre for Advanced Research
Cross-Layer Attention Probing for Fine-Grained Hallucination Detection
Sep 4, 2025Malavika Suresh, Rahaf Aljundi, Ikechukwu Nkisi-Orji +1LLM Hallucination Detection LLM Reliability
Robert Gordon University, Aberdeen, United Kingdom · Toyota Motor Europe, Brussels, Belgium
SAVER: Mitigating Hallucinations in Large Vision-Language Models via Style-Aware Visual Early Revision
Aug 5, 2025Zhaoxu Li, Chenqi Kong, Yi Yu +6VLM Evaluation LLM Hallucination Mitigation
ROSE Lab, Interdisciplinary Graduate Programme, Nanyang Technological University, Singapore · ROSE Lab, School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore · City University of Hong Kong, Hong Kong SAR +3
Towards Mitigation of Hallucination for LLM-empowered Agents: Progressive Generalization Bound Exploration and Watchdog Monitor
Jul 21, 2025Siyuan Liu, Wenjing Liu, Zhiwei Xu +3LLM Hallucination Mitigation Hallucination in Language Models
College of Computer Science, Nankai University · College of intelligent Science and Technology, Inner Mongolia University of Technology · Institute of Computing Technology, Chinese Academy of Sciences +3
Popular but Wrong: Understanding and Mitigating LLM Overconfidence through Knowledge Popularity
May 23, 2025Shiyu Ni, Keping Bi, Jiafeng Guo +1LLM Uncertainty Estimation LLM Hallucination Mitigation
CAS Key Lab of Network Data Science and Technology, ICT, CAS · State Key Laboratory of AI Safety · University of Chinese Academy of Sciences
Atomic Consistency Preference Optimization for Long-Form Question Answering
May 14, 2025Jingfeng Chen, Raghuveer Thirukovalluru, Junlin Wang +2LLM Hallucination Mitigation LLM Alignment
HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs
Mar 3, 2025Tin Nguyen, Logan Bolton, Mohammad Reza Taesiri +2LLM Grounding LLM Answer Verification
Auburn University · University of Alberta

Mar 20, 2026J/K move · Enter open · S save

Neural Uncertainty Principle: A Unified View of Adversarial Fragility and LLM Hallucination

Dong-Xiao Zhang, Hu Lou, Jun-Jie Zhang, Jun Zhu+1

Northwest Institute of Nuclear Technology, Xi’an, Shaanxi 710024, China. · Department of Computer Science and Technology, Institute for AI, BNRist Center, THBI Lab, Tsinghua-Bosch Joint Center for ML, Tsinghua University, Beijing 10084, China · the School of Mathematics and Statistics and the Ministry of Education Key Lab of Intelligent Networks and Network Security, Xi’an Jiaotong University, Xi’an, Shaanxi 710049, China.

Hallucination in Language Models Adversarial Robustness LLM Hallucination Mitigation LLM Hallucination Detection

Open paper AskPDF arXiv

Adversarial vulnerability in vision and hallucination in large language models are conventionally viewed as separate problems, each addressed with modality-specific patches. This study first reveals that they share a common geometric origin: the input and its loss gradient are conjugate observables subject to an irreducible uncertainty bound. Formalizing a Neural Uncertainty Principle (NUP) under a loss-induced state, we find that in near-bound regimes, further compression must be accompanied by increased sensitivity dispersion (adversarial fragility), while weak prompt-gradient coupling leaves generation under-constrained (hallucination). Crucially, this bound is modulated by an input-gradient correlation channel, captured by a specifically designed single-backward probe. In vision, masking highly coupled components improves robustness without costly adversarial training; in language, the same prefill-stage probe detects hallucination risk before generating any answer tokens. NUP thus turns two seemingly separate failure taxonomies into a shared uncertainty-budget view and provides a principled lens for reliability analysis. Guided by this NUP theory, we propose ConjMask (masking high-contribution input components) and LogitReg (logit-side regularization) to improve robustness without adversarial training, and use the probe as a decoding-free risk signal for LLMs, enabling hallucination detection and prompt selection. NUP thus provides a unified, practical framework for diagnosing and mitigating boundary anomalies across perception and generation tasks.