paper-with-me

홈 › Papers

MIND: Multi-rationale INtegrated Discriminative Reasoning Framework for Multi-modal Large Models

2025-12-05 · Chuang Yu, Jinmiao Zhao, Mingxuan Zhao, Yunpeng Liu, Xiujun Shu, Yuanhao Feng, Bo Wang, Xiangyu Yue arxiv

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 susceptibility to misleading cues. Therefore, we propose a Multi-rationale INtegrated Discriminative (MIND) reasoning framework, which is designed to endow MLLMs with human-like cognitive abilities of "Understand -> Rethink -> 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 provides 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. Extensive experiments show that our MIND achieves SOTA performance on multiple public datasets. Our data and code are available at https://github.com/YuChuang1205/MIND

📄 PDF Abstract BibTeX arXiv:2512.05530

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

SCRIPTMIND: Crime Script Inference and Cognitive Evaluation for LLM-based Social Engineering Scam Detection System

2026-01-20 · Heedou Kim, Changsik Kim, Sanghwa Shin, Jaewoo Kang arxiv

Social engineering scams increasingly employ personalized, multi-turn deception, exposing the limits of traditional detection methods. While Large Language Models (LLMs) show promise in identifying deception, their cogni…

LLM-Hanabi: Evaluating Multi-Agent Gameplays with Theory-of-Mind and Rationale Inference in Imperfect Information Collaboration Game

2025-10-06 · Fangzhou Liang, Tianshi Zheng, Chunkit Chan, Yauwai Yim 외 arxiv

Effective multi-agent collaboration requires agents to infer the rationale behind others' actions, a capability rooted in Theory-of-Mind (ToM). While recent Large Language Models (LLMs) excel at logical inference, their …

MIND: From Passive Mimicry to Active Reasoning through Capability-Aware Multi-Perspective CoT Distillation

2026-01-07 · Jin Cui, Jiaqi Guo, Jiepeng Zhou, Ruixuan Yang 외 arxiv

While Large Language Models (LLMs) have emerged with remarkable capabilities in complex tasks through Chain-of-Thought reasoning, practical resource constraints have sparked interest in transferring these abilities to sm…

Domain Generalization

UMind-VL: A Generalist Ultrasound Vision-Language Model for Unified Grounded Perception and Comprehensive Interpretation

2025-11-27 · Dengbo Chen, Ziwei Zhao, Kexin Zhang, Shishuang Zhao 외 arxiv

Despite significant strides in medical foundation models, the ultrasound domain lacks a comprehensive solution capable of bridging low-level Ultrasound Grounded Perception (e.g., segmentation, localization) and high-leve…

MindWatcher: Toward Smarter Multimodal Tool-Integrated Reasoning

2025-12-29 · Jiawei Chen, Xintian Shen, Lihao Zheng, Zhenwei Shao 외 arxiv

Traditional workflow-based agents exhibit limited intelligence when addressing real-world problems requiring tool invocation. Tool-integrated reasoning (TIR) agents capable of autonomous reasoning and tool invocation are…

Object RecognitionImage Retrieval