Object Hallucination in VLMs

VLM: Vision-Language Model

Ask about this topic

Overview

This topic studies when vision-language models mention objects that are absent, miss visible objects, or misread relationships in images and videos. Researchers evaluate these failures with captioning, question-answering, and grounding benchmarks such as CHAIR, POPE, and AMBER, and use controlled tests to separate weak perception from language-prior effects. Mitigation approaches include training-free contrastive decoding and attention or representation steering, as well as region-based verification, preference tuning, and reinforcement learning. A central challenge is reducing unsupported claims without suppressing correct details or harming fluency, while ensuring improvements hold across models, tasks, and evaluation methods.

Latest papers

CardsList

128 papers17 papers in the last four weeks, up 89% on the four weeks before. 0.1% of all new papers.

  1. Causal Decoding for Hallucination-Resistant Multimodal Large Language Models

    Feb 24, 2026Shiwei Tan, Hengyi Wang, Weiyi Qin +3Object Hallucination in VLMsVLM Hallucination Mitigation

    Rutgers University · Meta Ranking AI

  2. HIME: Mitigating Object Hallucinations in LVLMs via Hallucination Insensitivity Model Editing

    Feb 21, 2026Ahmed Akl, Abdelwahed Khamis, Ali Cheraghian +3Object Hallucination in VLMsVLM Hallucination Mitigation

    School of Information and Communication Technology, Griffith University, Australia · Data61, CSIRO, Australia · School of Engineering, Macquarie University, Sydney, Australia

  3. Revealing and Enhancing Core Visual Regions: Harnessing Internal Attention Dynamics for Hallucination Mitigation in LVLMs

    Feb 17, 2026Guangtao Lyu, Qi Liu, Chenghao Xu +5Attention Intervention in VLMsVLM Hallucination Mitigation

    School of Electronic Engineering, Xidian University, Xi’an, China · College of Computer and Information, Hohai University, Nanjing, China · School of Computer Science and Technology, Xidian University, Xi’an, China +1

  4. Attention-space Contrastive Guidance for Efficient Hallucination Mitigation in LVLMs

    Jan 20, 2026Yujin Jo, Sangyoon Bae, Taesup KimVLM Hallucination MitigationObject Hallucination in VLMs

    Seoul National University

  5. Semantic Misalignment in Vision-Language Models under Perceptual Degradation

    Jan 13, 2026Guo Cheng, Huang LiVLM EvaluationVLM Robustness

  6. Constructive Distortion: Improving MLLMs with Attention-Guided Image Warping

    Oct 10, 2025Dwip Dalal, Gautam Vashishtha, Utkarsh Mishra +6Object Hallucination in VLMsMultimodal Large Language Models

    University of Illinois Urbana–Champaign · Skan AI · Texas A&M University +1

  7. Mitigating Hallucinations via Inter-Layer Consistency Aggregation in Large Vision-Language Models

    May 18, 2025Kai Tang, Jinhao You, Yichen Guo +8Vision-Language ModelsHallucination in Language Models

    Peking University · University of Pennsylvania · Nanyang Technological University +4

  8. SpurLens: Automatic Detection of Spurious Cues in Multimodal LLMs

    Mar 11, 2025Parsa Hosseini, Sumit Nawathe, Mazda Moayeri +2VLM EvaluationVLM Robustness

    Department of Computer Science University of Maryland