Pseudo-Siamese Network for Planning in Target-Oriented Proactive Dialogues

面向目标导向主动对话的伪孪生规划网络

Abstract: A target-oriented proactive dialogue system is designed to steer conversations toward predefined targets while actively providing suggestions. The core paradigm of such a system is to plan a reasonable dialogue path and subsequently guide language models (e.g., pre-trained or large language models) to generate responses, where dialogue path planning serves as the central component-a novel yet under-explored problem.

摘要： 目标导向型主动对话系统旨在引导对话走向预设目标，同时主动提供建议。此类系统的核心范式是规划出合理的对话路径，并据此引导语言模型（如预训练模型或大语言模型）生成回复。其中，对话路径规划作为核心组件，是一个新颖但尚未被充分探索的问题。

In this work, we propose a Forward-Focused Bidirectional Pseudo-Siamese Network (FF-BPSN) for dialogue path planning toward predefined dialogue targets. FF-BPSN employs two identical transformer-based decoders for forward and backward planning, together with a forward-focused module that integrates bidirectional information to construct the final forward path. This path benefits from bidirectional planning while prioritizing forward information.

在这项工作中，我们提出了一种面向预设对话目标的“前向聚焦双向伪孪生网络”（FF-BPSN）用于对话路径规划。FF-BPSN 采用两个相同的基于 Transformer 的解码器分别进行前向和后向规划，并结合一个前向聚焦模块，整合双向信息以构建最终的前向路径。该路径既受益于双向规划的优势，又优先考虑了前向信息。

We then employ the planned path to guide language models in response generation. Extensive experiments on DuRecDial and DuRecDial 2.0 demonstrate that FF-BPSN achieves state-of-the-art performance in dialogue path planning and significantly enhances the effectiveness of target-oriented proactive dialogue systems.

随后，我们利用规划出的路径来引导语言模型生成回复。在 DuRecDial 和 DuRecDial 2.0 数据集上的大量实验表明，FF-BPSN 在对话路径规划方面达到了最先进（SOTA）的性能，并显著提升了目标导向型主动对话系统的有效性。