动态协调常识知识，让对话更懂共情。
Dynamic Commonsense Coordination for Empathetic Response Generation
- 分阶段动态整合上下文与情境常识，避免固定表示限制。
- 在情感识别上准确率提升，回复多样性显著增强。
- 适合需要高共情能力的聊天机器人研发者使用。
共情对话生成（ERG）要求模型识别用户情绪并生成共情回应。常识知识有助于此类推理，但现有方法通常在理解与生成阶段复用固定的常识表征，限制了跨阶段的知识协调。本文提出动态常识协调框架DCC，包含三个互补模块：基于残差的常识交互（SCE-AttnRes）用于融合上下文与情境常识表征，关联引导的常识过滤（AGCF）用于抑制低相关性常识关系，迭代式常识感知解码（ICAD）在生成过程中动态检索常识记忆。在Empathetic-Dialogues基准上的实验表明，DCC在保持与基线模型相当困惑度的同时，提升了情绪分类准确率和回复多样性。基于大模型的盲评进一步验证，DCC生成的回应具有更高的相关性、连贯性和信息量。代码与实现细节将公开于https://github.com/Hanabi-Q/DCC-ERG。
原文摘要 · Abstract (English)
Empathetic Response Generation (ERG) requires models to recognize users' emotions and generate empathetic responses. Commonsense knowledge has been shown to support such reasoning, yet existing approaches typically reuse fixed commonsense representations across understanding and generation, limiting their ability to coordinate such knowledge across different stages. We propose DCC, a Dynamic Commonsense Coordination Framework with three complementary modules: residual-based commonsense interaction (SCE-AttnRes) to integrate contextual and situational commonsense representations, Association-Guided Commonsense Filtering (AGCF) to down-weight low-relevance commonsense relations, and Iterative Commonsense-Aware Decoding (ICAD) to dynamically retrieve commonsense memories during generation. Experiments on the Empathetic-Dialogues benchmark show that DCC improves emotion classification accuracy and response diversity over the CEM baseline while maintaining comparable perplexity. An LLM-based blind evaluation further demonstrates that DCC generates responses with better relevance, coherence, and informativeness. The code and implementation details will be publicly available at https://github.com/Hanabi-Q/DCC-ERG.
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。