用强化学习提升多模态情绪识别模型的推理与泛化能力
R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning
- 引入可验证奖励的强化学习优化多模态大模型
- 在分布内和分布外数据上均显著提升情绪识别准确率
- 可解释推理过程，明确视觉与音频的贡献差异
本文首次将可验证奖励的强化学习（RLVR）应用于多模态大语言模型的情绪识别任务，该任务中视觉与音频模态均至关重要。通过RLVR优化，模型在推理能力、情绪识别准确率和泛化性能三方面均显著提升。该方法不仅增强了模型在分布内数据上的表现，还在分布外数据上展现出更强鲁棒性。更重要的是，改进后的推理能力使得能够清晰分析不同模态（尤其是视觉与音频信息）在情绪识别过程中的贡献，为多模态大语言模型的优化提供了重要洞察。
原文摘要 · Abstract (English)
In this work, we present the first application of Reinforcement Learning with Verifiable Reward (RLVR) to an Omni-multimodal large language model in the context of emotion recognition, a task where both visual and audio modalities play crucial roles. We leverage RLVR to optimize the Omni model, significantly enhancing its performance in three key aspects: reasoning capability, emotion recognition accuracy, and generalization ability. The introduction of RLVR not only improves the model's overall performance on in-distribution data but also demonstrates superior robustness when evaluated on out-of-distribution datasets. More importantly, the improved reasoning capability enables clear analysis of the contributions of different modalities, particularly visual and audio information, in the emotion recognition process. This provides valuable insights into the optimization of multimodal large language models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。