C2F-Thinker: Coarse-to-Fine Reasoning with Hint-Guided Reinforcement Learning for Multimodal Sentiment Analysis
C2F-Thinker:基于提示引导强化学习的粗到细推理用于多模态情感分析
机构 * School of Computer Science, South China Normal University(华南师范大学计算机科学学院) ; School of Electronic and Information Engineering, South China University of Technology(华南理工大学电子与信息工程学院)
专题命中 测试时计算 :reasoning(title,abstract);chain-of-thought(abstract);CoT(abstract);分类 cs.CL、cs.AI
AI总结 本文提出C2F-Thinker框架,通过粗到细结构推理与提示引导强化学习,提升多模态情感分析的可解释性和泛化能力。