用扩散模型实现非序列对话规划，避免逐步错误累积。
Planning with Diffusion Models for Target-Oriented Dialogue Systems
- 将对话规划建模为带条件引导的轨迹生成问题
- 在三个场景中实现长程策略优化，效果优于传统方法
- 支持多种目标类型，适合复杂多变的对话任务
目标导向对话（TOD）在大模型时代仍面临挑战，战略性的对话规划对引导对话达成特定目标至关重要。然而现有方法采用逐步序列生成对话计划，易产生误差累积和短视行为。为此，我们提出新框架DiffTOD，利用扩散模型实现非序列对话规划。DiffTOD将对话规划视为带条件引导的轨迹生成问题，采用扩散语言模型估计对话轨迹概率。为优化对话动作策略，引入三种针对不同目标类型的定制化引导机制，可在测试时灵活引导。在三个多样化的TOD设置中进行的大量实验表明，DiffTOD能有效进行非短视的前瞻探索，并通过非序列规划在长时程上优化行动策略，在复杂多变的对话场景中展现强灵活性。代码与数据已公开于https://github.com/ninglab/DiffTOD。
原文摘要 · Abstract (English)
Target-Oriented Dialogue (TOD) remains a significant challenge in the LLM era, where strategic dialogue planning is crucial for directing conversations toward specific targets. However, existing dialogue planning methods generate dialogue plans in a step-by-step sequential manner, and may suffer from compounding errors and myopic actions. To address these limitations, we introduce a novel dialogue planning framework, DiffTOD, which leverages diffusion models to enable non-sequential dialogue planning. DiffTOD formulates dialogue planning as a trajectory generation problem with conditional guidance, and leverages a diffusion language model to estimate the likelihood of the dialogue trajectory. To optimize the dialogue action strategies, DiffTOD introduces three tailored guidance mechanisms for different target types, offering flexible guidance toward diverse TOD targets at test time. Extensive experiments across three diverse TOD settings show that DiffTOD can effectively perform non-myopic lookahead exploration and optimize action strategies over a long horizon through non-sequential dialogue planning, and demonstrates strong flexibility across complex and diverse dialogue scenarios. Our code and data are accessible through https://github.com/ninglab/DiffTOD.
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。