从成功与失败中学习：为社交机器人获取自适应对话策略
Learning from Success and Failure: Acquiring Adaptive Dialogue Strategies for Social Robots
- CyberAgent
- The University of Osaka（大阪大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究提出利用视觉语言模型和大语言模型，从成功与失败交互中自动获取社交机器人对话策略，显式表示失败策略可提升性能，并降低开发成本。
AI中文摘要：
传统社交机器人对话系统需要同时具备对话策略和用户属性识别能力，这两者均需专门的专业知识。然而，在实际部署中数据收集成本高昂，且由此产生的数据集往往包含大量失败案例。在本研究中，我们旨在利用视觉语言模型（VLM）和大语言模型（LLM），通过利用成功与失败的交互来自动获取对话策略。我们提出了一种架构，其中由VLM识别的用户属性与对话历史一起输入LLM，以生成针对特定用户属性的对话策略。我们从现场实验收集的交互数据集中提取对话策略，并评估其有效性。结果表明，显式表示失败策略可补充成功策略并提升性能。我们的发现突显了一种实用的流程，即通过将大量失败交互回收为可复用的约束，从实际部署日志中构建和维护可解释的策略库，最终降低社交机器人的开发成本。
英文摘要：
Traditional dialogue systems for social robots require both dialogue strategies and user attribute recognition, each demanding specialized expertise. However, data collection is costly in real-world deployments, and the resulting datasets often include many failure cases. In this study, we aim to automate the acquisition of dialogue strategies by leveraging both successful and failed interactions using a vision-language model (VLM) and a large language model (LLM). We propose an architecture in which user attributes, recognized by the VLM, along with dialogue history, are fed into the LLM to generate dialogue strategies tailored to specific user attributes. We extracted dialogue strategies from an interaction dataset collected through a field experiment and evaluated their effectiveness. The results demonstrate that explicitly representing failure strategies complements success strategies and improves performance. Our findings highlight a practical pipeline for constructing and maintaining an interpretable strategy repository from in-the-wild deployment logs by recycling abundant failure interactions as reusable constraints, ultimately reducing the development cost of social robots.
