通过反思与修正提升对话系统响应一致性
Enhancing Goal-oriented Proactive Dialogue Systems via Consistency Reflection and Correction
- 分两阶段：先反思不一致，再修正生成内容
- 在多个大模型上验证，显著提升响应一致性
- 适合需要高可靠性的智能客服与助手场景
面向目标的主动对话系统旨在通过规划目标导向路径，引导用户对话顺利达成特定目标。然而，以往研究主要聚焦于路径优化，忽略了生成回应与对话上下文（包括用户画像、对话历史、领域知识和子目标）之间的不一致性问题。为此，我们提出一种模型无关的两阶段一致性反思与修正（CRC）框架。第一阶段，模型被提示反思生成回应与上下文之间的差异，识别不一致并提出可能修正方案；第二阶段，基于反思结果生成更符合上下文的回应。我们在多种模型架构（包括BART、T5、GPT-2、DialoGPT、Phi3、Mistral和LLaMA3）及不同参数规模下进行了实验，结果在三个数据集上均表明，该框架显著提升了生成回应与对话上下文的一致性。
原文摘要 · Abstract (English)
Goal-oriented proactive dialogue systems are designed to guide user conversations seamlessly towards specific objectives by planning a goal-oriented path. However, previous research has focused predominantly on optimizing these paths while neglecting the inconsistencies that may arise between generated responses and dialogue contexts, including user profiles, dialogue history, domain knowledge, and subgoals. To address this issue, we introduce a model-agnostic two-stage Consistency Reflection and Correction (CRC) framework. Specifically, in the consistency reflection stage, the model is prompted to reflect on the discrepancies between generated responses and dialogue contexts, identifying inconsistencies and suggesting possible corrections. In the consistency correction stage, the model generates responses that are more consistent with the dialogue context based on these reflection results. We conducted experiments on various model architectures with different parameter sizes, including encoder-decoder models (BART, T5) and decoder-only models (GPT-2, DialoGPT, Phi3, Mistral and LLaMA3), and the experimental results on three datasets demonstrate that our CRC framework significantly improves the consistency between generated responses and dialogue contexts.
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。