Emotional Hallucination in VLMs

VLM: Vision-Language Model

Follow this topic Ask about this topic

Latest papers

8 papers0 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

RelCheck: Dual-Evidence Spatial Grounding for VLM Hallucination Correction
Aug 21, 2026Siddhi Patil, Navrati Saxena, William B. AndreopoulosEmotional Hallucination in VLMs VLM Hallucination Mitigation
Dept. of Computer Science San Jos´e State University
When Visual Signals Mislead: A Mechanistic Study of Attribute Hallucination in Vision-Language Models
Aug 11, 2026Yufei Zhang, Chenlu Zhan, Hongwei WangHallucination Detection in VLMs VLM Adaptation
Zhejiang University
When Model Priors Conflict with Visual Evidence: Mitigating Commonsense-Driven Hallucinations by Selective Prior Calibration
Jul 31, 2026Kesheng Chen, Yamin Hu, Wenjian LuoVLM Hallucination Emotional Hallucination in VLMs
Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies Institute of Cyberspace Security School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China
Contextualized Evaluation of Vision Language Models through Dynamic, Multi-turn Interactions
Jul 16, 2026Yijiang Li, Huiqi Zou, Bingyang Wang +1VLM Evaluation VLM Hallucination
UC San Diego · Northeastern University · Georgia Institute of Technology +1
Mirage Probes: How Vision Models Fake Visual Understanding
Jun 11, 2026Daniel Ben-Levi, Judah Goldfeder, Weiliang Zhao +5Vision-Language Models Emotional Hallucination in VLMs
Columbia University · Intuit · Technion +2
Interpreting and Enhancing Emotional Circuits in Large Vision-Language Models via Cross-Modal Information Flow
May 21, 2026Chengsheng Zhang, Chenghao Sun, Zhining Xie +1VLM Hallucination Emotional Hallucination in VLMs
MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, University of Science and Technology of China · AIPD, Tencent
Attention at Rest Stays at Rest: Breaking Visual Inertia to Mitigate Relation Hallucinations
Apr 2, 2026Boyang Gong, Yu Zheng, Fanye Kong +2Emotional Hallucination in VLMs VLM Hallucination Mitigation
Tsinghua University
CDH-Bench: A Commonsense-Driven Hallucination Benchmark for Evaluating Visual Fidelity in Vision-Language Models
Mar 30, 2026Kesheng Chen, Yamin Hu, Qi Zhou +2Emotional Hallucination in VLMs VLM Hallucination
Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies, Institute of Cyberspace Security, School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China

Aug 21, 2026J/K move · Enter open · S save

RelCheck: Dual-Evidence Spatial Grounding for VLM Hallucination Correction

Siddhi Patil, Navrati Saxena, William B. Andreopoulos

Dept. of Computer Science San Jos´e State University

Emotional Hallucination in VLMs VLM Hallucination Mitigation Vision-Language Grounding Visual Spatial Reasoning

Open paper AskPDF arXiv

Multimodal large language models (MLLMs) fre- quently generate text that is inconsistent with the input image. While object- and attribute-level hallucinations have received considerable attention, relational hallucinations (incorrect de- scriptions of spatial or interactive relationships between objects) remain largely unaddressed by existing post-hoc correction methods. We present RelCheck, a training-free post-hoc correction pipeline that augments object-level visual grounding with dual relational evidence: learned scene-graph triples from RelTR and deterministic spatial predicates from bounding-box geometry. These combine with a Woodpecker-style object claim layer to form a three-layer visual knowledge base, which a language model corrector uses to rewrite hallucinated text. Evaluated on LLaVA v1 13B, RelCheck achieves a total MME hallucination score of 630.0 versus 585.0 for a Woodpecker-style baseline, with the largest gain on the position subtask (+31.7 points, accuracy+ improving from 0.367 to 0.600). A four-configuration ablation confirms that both relational layers contribute independently (McNemar p = 0.025). These results show that structured relational evidence meaningfully improves post-hoc hallucination correction on the spatial reasoning subtasks where current MLLMs are most deficient.