{"ID":2832473,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.05530","arxiv_id":"2512.05530","title":"MIND: Multi-rationale INtegrated Discriminative Reasoning Framework for Multi-modal Large Models","abstract":"Recently, multimodal large language models (MLLMs) have been widely applied to reasoning tasks. However, they suffer from limited multi-rationale semantic modeling, insufficient logical robustness, and are susceptible to misleading interpretations in complex scenarios. Therefore, we propose a Multi-rationale INtegrated Discriminative (MIND) reasoning framework, which is designed to endow MLLMs with human-like cognitive abilities of \"Understand -\u003e Rethink -\u003e Correct\", and achieves a paradigm evolution from passive imitation-based reasoning to active discriminative reasoning. Specifically, we introduce a Rationale Augmentation and Discrimination (RAD) paradigm, which automatically and efficiently expands existing datasets by generating diverse rationales, providing a unified and extensible data foundation. Meanwhile, we design a Progressive Two-stage Correction Learning (P2CL) strategy. The first phase enhances multi-rationale positive learning, while the second phase enables active logic discrimination and correction. In addition, to mitigate representation entanglement in the multi-rationale semantic space, we propose a Multi-rationale Contrastive Alignment (MCA) optimization strategy, which achieves semantic aggregation of correct reasoning and boundary separation of incorrect reasoning. Extensive experiments demonstrate that the proposed MIND reasoning framework achieves state-of-the-art (SOTA) performance on multiple public datasets covering scientific, commonsense, and mathematical scenarios. It provides a new perspective for advancing MLLMs towards higher levels of cognitive intelligence. Our code is available at https://github.com/YuChuang1205/MIND","short_abstract":"Recently, multimodal large language models (MLLMs) have been widely applied to reasoning tasks. However, they suffer from limited multi-rationale semantic modeling, insufficient logical robustness, and are susceptible to misleading interpretations in complex scenarios. Therefore, we propose a Multi-rationale INtegrated...","url_abs":"https://arxiv.org/abs/2512.05530","url_pdf":"https://arxiv.org/pdf/2512.05530v1","authors":"[\"Chuang Yu\",\"Jinmiao Zhao\",\"Mingxuan Zhao\",\"Yunpeng Liu\",\"Xiujun Shu\",\"Yuanhao Feng\",\"Bo Wang\",\"Xiangyu Yue\"]","published":"2025-12-05T08:41:44Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":606234,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2832473,"paper_url":"https://arxiv.org/abs/2512.05530","paper_title":"MIND: Multi-rationale INtegrated Discriminative Reasoning Framework for Multi-modal Large Models","repo_url":"https://github.com/YuChuang1205/MIND","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}