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
C2F-Thinker: Coarse-to-Fine Reasoning with Hint-Guided Reinforcement Learning for Multimodal Sentiment Analysis
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。
摘要：
多模态情感分析旨在整合文本、声音和视觉信息以实现深入的情感理解。尽管通过监督微调取得了多模态大语言模型（MLLMs）的进步，但其“黑箱”性质阻碍了可解释性。尽管链式推理（CoT）提供了一种潜在的解决方案，但其受到高人工标注成本和强化学习（RL）固有挑战（如奖励稀疏性和在困难样本上的探索效率低）的限制。本文提出C2F-Thinker，通过两阶段渐进训练流程，将粗到细的结构推理与提示引导的RL相结合。第一阶段通过高质量的CoT数据进行冷启动监督微调，包含三个阶段：极性判断、中间分析和细粒度评分。这使基础模型具备结构化情感推理范式。第二阶段引入提示引导的组相对策略优化（GRPO）算法。通过在采样过程中注入正确的初始极性预测作为提示，模型被引导至准确的推理路径，有效缓解级联误差并提高困难样本的利用效率。此外，设计了多方面的奖励函数，结合分类、回归和格式约束，以在提升预测准确性的同时保持可解释性。实验结果表明，C2F-Thinker在细粒度情感回归任务中表现竞争，同时在跨领域泛化方面显著优于基线模型。这突显了其在构建可信、稳健的情感分析系统以应用于现实世界中的潜力。
英文摘要：
Multimodal sentiment analysis aims to integrate textual, acoustic, and visual information for deep emotional understanding. Despite the progress of multimodal large language models (MLLMs) via supervised fine-tuning, their "black-box" nature hinders interpretability. While Chain-of-Thought (CoT) reasoning offers a potential remedy, it is constrained by high manual annotation costs and the inherent challenges of reinforcement learning (RL), such as reward sparsity and low exploration efficiency on hard samples. This paper presents C2F-Thinker, a framework that harmonizes coarse-to-fine structured reasoning with hint-guided RL through a two-stage progressive training pipeline. In the first stage, we conduct cold-start supervised fine-tuning using high-quality CoT data distilled from a larger teacher model, consisting of three distinct phases: polarity judgment, intermediate analysis, and fine-grained scoring. This equips the base model with a structured emotional reasoning paradigm. In the second stage, we introduce a hint-guided Group Relative Policy Optimization (GRPO) algorithm. By injecting correct initial polarity predictions as hints during the sampling process, the model is guided toward accurate reasoning paths, effectively mitigating cascading errors and enhancing the utilization of hard samples. Furthermore, a multi-faceted reward function incorporating classification, regression, and formatting constraints is designed to refine prediction accuracy while preserving interpretability. Experimental results demonstrate that C2F-Thinker achieves competitive performance on fine-grained sentiment regression tasks while significantly outperforming baselines in cross-domain generalization. This highlights its potential in building trustworthy and robust sentiment analysis systems for real-world applications.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
