为用户模拟器生成多样化角色以测试面试对话系统
Generating Diverse Personas for User Simulators to Test Interview Dialogue Systems
浏览论文内容
中文总结 AI 辅助
针对面试对话系统测试人力成本高的问题，提出用大语言模型自动生成带沟通风格人格特质的多样化角色的用户模拟器，实验显示其生成话语的变化性更大。
中文摘要 AI 辅助
本文解决了测试面试对话系统需要大量人力的问题。尽管面试对话系统有望在各种场景中发挥作用，但与其他对话系统一样，用人类用户测试它们需要付出巨大的努力和成本。因此，使用用户模拟器进行测试可能会带来益处。由于大多数传统用户模拟器主要是为训练任务型对话系统而设计的，人们对模拟用户的角色关注甚少。在开发过程中，测试面试对话系统需要模拟广泛的用户行为，但手动创建大量角色是劳动密集型的。我们提出了一种使用大语言模型自动为用户模拟器生成角色的方法。此外，通过在生成角色时赋予与沟通风格相关的人格特质，我们旨在提高用户模拟器中沟通风格的多样性。实验结果表明，所提出的方法能让用户模拟器生成具有更大变化性的话语。
英文摘要
This paper addresses the issue of the significant labor required to test interview dialogue systems. While interview dialogue systems are expected to be useful in various scenarios, like other dialogue systems, testing them with human users requires significant effort and cost. Therefore, testing with user simulators can be beneficial. Since most conventional user simulators have been primarily designed for training task-oriented dialogue systems, little attention has been paid to the personas of the simulated users. During development, testing interview dialogue systems requires simulating a wide range of user behaviors, but manually creating a large number of personas is labor-intensive. We propose a method that automatically generates personas for user simulators using a large language model. Furthermore, by assigning personality traits related to communication styles when generating personas, we aim to increase the diversity of communication styles in the user simulator. Experimental results show that the proposed method enables the user simulator to generate utterances with greater variation.
发表机构
- C4A Research Institute, Inc.（C4A研究所）
- SANKEN, University of Osaka（大阪大学SANKEN研究所）
- Musashi University（武藏野大学）
机构由 AI 辅助整理，请以论文原文为准。
