让对话模型提前预测用户意图，减少重复问答
Proactive Dialogue Model with Intent Prediction
- 用时间贝叶斯网络建模意图转移规律，轻量注入提示词
- 在多意图场景下，意图覆盖速度提升30.6%，对话轮次减少31%
- 无需修改模型，适合想提升对话效率的开发者
对话模型天生被动，仅响应当前用户输入而无法预判后续意图，导致多意图场景下交互冗余。本文提出一种轻量级意图转移先验，基于多轮对话数据构建，并在推理时注入系统提示。该先验通过在MultiWOZ 2.2数据集上训练的时间贝叶斯网络（T-BN）实现，对1,071个保留的用户轮次，召回率@5达0.787，平均秩次（MRR）为0.576。在200个对话的真值回放实验中，基于贝叶斯网络引导生成使意图覆盖的AUC从0.742提升至0.856，达到75%意图覆盖率所需轮次从3.95降至2.73。结果表明，轻量级意图转移引导可在不修改底层语言模型的前提下，显著提升对话的主动性与效率。
原文摘要 · Abstract (English)
Dialogue models are inherently reactive, responding to the current user turn without anticipating upcoming intents, which leads to redundant interactions in multi-intent settings. We address this limitation by introducing a lightweight intent-transition prior derived from dialogue data and injected into the system prompt at inference time. We instantiate this prior using a Temporal Bayesian Network (T-BN) trained on per-turn intent annotations in MultiWOZ 2.2. The T-BN achieves Recall@5 = 0.787 and MRR = 0.576 on 1,071 held-out USER-turn pairs. In a ground-truth replay over 200 dialogues, BN-guided generation improves Coverage AUC from 0.742 to 0.856 and reduces the number of turns required to reach 75% intent coverage from 3.95 to 2.73. These results show that lightweight intent-transition guidance enables more proactive and efficient dialogue behavior without modifying the underlying language model.
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。