{"ID":2882224,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.10444","arxiv_id":"2508.10444","title":"DiFaR: Enhancing Multimodal Misinformation Detection with Diverse, Factual, and Relevant Rationales","abstract":"Generating textual rationales from large vision-language models (LVLMs) to support trainable multimodal misinformation detectors has emerged as a promising paradigm. However, its effectiveness is fundamentally limited by three core challenges: (i) insufficient diversity in generated rationales, (ii) factual inaccuracies due to hallucinations, and (iii) irrelevant or conflicting content that introduces noise. We introduce DiFaR, a detector-agnostic framework that produces diverse, factual, and relevant rationales to enhance misinformation detection. DiFaR employs five chain-of-thought prompts to elicit varied reasoning traces from LVLMs and incorporates a lightweight post-hoc filtering module to select rationale sentences based on sentence-level factuality and relevance scores. Extensive experiments on four popular benchmarks demonstrate that DiFaR outperforms four baseline categories by up to 5.9% and boosts existing detectors by as much as 8.7%. Both automatic metrics and human evaluations confirm that DiFaR significantly improves rationale quality across all three dimensions.","short_abstract":"Generating textual rationales from large vision-language models (LVLMs) to support trainable multimodal misinformation detectors has emerged as a promising paradigm. However, its effectiveness is fundamentally limited by three core challenges: (i) insufficient diversity in generated rationales, (ii) factual inaccuracie...","url_abs":"https://arxiv.org/abs/2508.10444","url_pdf":"https://arxiv.org/pdf/2508.10444v1","authors":"[\"Herun Wan\",\"Jiaying Wu\",\"Minnan Luo\",\"Xiangzheng Kong\",\"Zihan Ma\",\"Zhi Zeng\"]","published":"2025-08-14T08:32:31Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Language Model\"]","has_code":false}