解码流动：面向长对话情感因果分析的CauseMotion
Decoding the Flow: CauseMotion for Emotional Causality Analysis in Long-form Conversations
AI总结：
针对长对话情感因果推理难题，提出结合RAG与多模态融合的CauseMotion框架，通过引入音频特征和滑动窗口机制增强因果链推断，构建首个超70轮长序列基准数据集，并在因果准确率上超越GPT-4o。
摘要：
长序列因果推理旨在揭示扩展时间序列数据中的因果关系，但受到复杂依赖关系和因果联系验证挑战的阻碍。为解决大规模语言模型（如GPT-4）在扩展对话中捕捉复杂情感因果关系的局限性，我们提出了CauseMotion，一个基于检索增强生成（RAG）和多模态融合的长序列情感因果推理框架。与仅依赖文本信息的传统方法不同，CauseMotion通过将音频衍生特征——声音情感、情感强度和语速——融入文本模态来丰富语义表示。通过将RAG与滑动窗口机制相结合，它能够有效检索并利用上下文相关的对话片段，从而推断跨越多个对话轮次的复杂情感因果链。为评估其有效性，我们构建了首个专门用于长序列情感因果推理的基准数据集，其中包含超过70轮次的对话。实验结果表明，所提出的基于RAG的多模态集成方法显著增强了对大规模语言模型的情感理解深度和因果推理能力。集成CauseMotion的GLM-4在因果准确率上比原始模型提高了8.7%，并比GPT-4o高出1.2%。此外，在公开的DiaASQ数据集上，CauseMotion-GLM-4在准确率、F1分数和因果推理准确率方面均取得了最先进的结果。
英文摘要：
Long-sequence causal reasoning seeks to uncover causal relationships within extended time series data but is hindered by complex dependencies and the challenges of validating causal links. To address the limitations of large-scale language models (e.g., GPT-4) in capturing intricate emotional causality within extended dialogues, we propose CauseMotion, a long-sequence emotional causal reasoning framework grounded in Retrieval-Augmented Generation (RAG) and multimodal fusion. Unlike conventional methods relying only on textual information, CauseMotion enriches semantic representations by incorporating audio-derived features-vocal emotion, emotional intensity, and speech rate-into textual modalities. By integrating RAG with a sliding window mechanism, it effectively retrieves and leverages contextually relevant dialogue segments, thus enabling the inference of complex emotional causal chains spanning multiple conversational turns. To evaluate its effectiveness, we constructed the first benchmark dataset dedicated to long-sequence emotional causal reasoning, featuring dialogues with over 70 turns. Experimental results demonstrate that the proposed RAG-based multimodal integrated approach, the efficacy of substantially enhances both the depth of emotional understanding and the causal inference capabilities of large-scale language models. A GLM-4 integrated with CauseMotion achieves an 8.7% improvement in causal accuracy over the original model and surpasses GPT-4o by 1.2%. Additionally, on the publicly available DiaASQ dataset, CauseMotion-GLM-4 achieves state-of-the-art results in accuracy, F1 score, and causal reasoning accuracy.
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。
