LLM Hallucination Mitigation

LLM: Large Language Model

Overview

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

CardsList

186 papers9 papers in the last four weeks, down 25% on the four weeks before. 0.1% of all new papers.

  1. SAVER: Mitigating Hallucinations in Large Vision-Language Models via Style-Aware Visual Early Revision

    Aug 5, 2025Zhaoxu Li, Chenqi Kong, Yi Yu +6VLM EvaluationLLM Hallucination Mitigation

  2. 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 MitigationHallucination in Language Models

  3. Popular but Wrong: Understanding and Mitigating LLM Overconfidence through Knowledge Popularity

    May 23, 2025Shiyu Ni, Keping Bi, Jiafeng Guo +1LLM Uncertainty EstimationLLM Hallucination Mitigation

  4. HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs

    Mar 3, 2025Tin Nguyen, Logan Bolton, Mohammad Reza Taesiri +2LLM GroundingLLM Answer Verification