Hexa：面向知识接地对话系统的自我改进
Hexa: Self-Improving for Knowledge-Grounded Dialogue System
AI总结：
针对知识接地对话中中间步骤真值数据缺失的问题，本文提出Hexa自我改进方法，通过引导式提示与改进损失函数进行自举训练，提升中间及最终回复生成性能。
摘要：
在知识接地对话生成中，一种常见做法是采用模块化方法显式利用中间步骤（例如网络搜索、记忆检索）。然而，与对话回复的数据相比，此类步骤的数据通常无法获得，因为它们在普通对话中是不可观测的。为弥补这些数据的缺失，我们开发了一种自我改进方法，可在没有真值数据的情况下提升中间步骤的生成性能。具体而言，我们提出了一种新颖的自举方案，结合引导式提示和改进的损失函数，以增强适当自生成回复的多样性。通过在多个基准数据集上的实验，我们从经验上证明，该方法成功利用自我改进机制生成中间回复和最终回复，并提升了知识接地对话生成任务的性能。
英文摘要：
A common practice in knowledge-grounded dialogue generation is to explicitly utilize intermediate steps (e.g., web-search, memory retrieval) with modular approaches. However, data for such steps are often inaccessible compared to those of dialogue responses as they are unobservable in an ordinary dialogue. To fill in the absence of these data, we develop a self-improving method to improve the generative performances of intermediate steps without the ground truth data. In particular, we propose a novel bootstrapping scheme with a guided prompt and a modified loss function to enhance the diversity of appropriate self-generated responses. Through experiments on various benchmark datasets, we empirically demonstrate that our method successfully leverages a self-improving mechanism in generating intermediate and final responses and improves the performances on the task of knowledge-grounded dialogue generation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
