{"ID":2888036,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.00726","arxiv_id":"2508.00726","title":"MIHBench: Benchmarking and Mitigating Multi-Image Hallucinations in Multimodal Large Language Models","abstract":"Despite growing interest in hallucination in Multimodal Large Language Models, existing studies primarily focus on single-image settings, leaving hallucination in multi-image scenarios largely unexplored. To address this gap, we conduct the first systematic study of hallucinations in multi-image MLLMs and propose MIHBench, a benchmark specifically tailored for evaluating object-related hallucinations across multiple images. MIHBench comprises three core tasks: Multi-Image Object Existence Hallucination, Multi-Image Object Count Hallucination, and Object Identity Consistency Hallucination, targeting semantic understanding across object existence, quantity reasoning, and cross-view identity consistency. Through extensive evaluation, we identify key factors associated with the occurrence of multi-image hallucinations, including: a progressive relationship between the number of image inputs and the likelihood of hallucination occurrences; a strong correlation between single-image hallucination tendencies and those observed in multi-image contexts; and the influence of same-object image ratios and the positional placement of negative samples within image sequences on the occurrence of object identity consistency hallucination. To address these challenges, we propose a Dynamic Attention Balancing mechanism that adjusts inter-image attention distributions while preserving the overall visual attention proportion. Experiments across multiple state-of-the-art MLLMs demonstrate that our method effectively reduces hallucination occurrences and enhances semantic integration and reasoning stability in multi-image scenarios.","short_abstract":"Despite growing interest in hallucination in Multimodal Large Language Models, existing studies primarily focus on single-image settings, leaving hallucination in multi-image scenarios largely unexplored. To address this gap, we conduct the first systematic study of hallucinations in multi-image MLLMs and propose MIHBe...","url_abs":"https://arxiv.org/abs/2508.00726","url_pdf":"https://arxiv.org/pdf/2508.00726v1","authors":"[\"Jiale Li\",\"Mingrui Wu\",\"Zixiang Jin\",\"Hao Chen\",\"Jiayi Ji\",\"Xiaoshuai Sun\",\"Liujuan Cao\",\"Rongrong Ji\"]","published":"2025-08-01T15:49:29Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}