释放用户反馈的潜力：利用大语言模型作为用户模拟器来增强对话系统
Unlocking the Potential of User Feedback: Leveraging Large Language Model as User Simulator to Enhance Dialogue System
AI总结：
针对大语言模型直接用于任务型对话表现不佳的问题，提出UGRO方法，将LLM作为无标注用户模拟器评估对话响应，结合较小的微调TOD模型生成高满意度回复，在两个TOD基准上超越了先前SOTA结果。
摘要：
对话系统和大语言模型（LLMs）已经引起了广泛关注。然而，与较小的任务特定模型相比，直接将LLMs用作任务型对话（TOD）模型的表现被发现不佳。尽管如此，认识到LLMs的巨大潜力并探索利用其卓越能力的改进方法至关重要。受利用LLMs的目标驱动，我们提出了一种称为用户引导的响应优化（UGRO）的替代方法，将其与较小的TOD模型相结合。该方法将LLM作为无标注的用户模拟器来评估对话响应，并将其与较小的微调端到端TOD模型相结合。通过利用LLMs生成的满意度反馈，UGRO进一步优化了监督微调的TOD模型。具体而言，TOD模型将对话历史作为输入，并在用户模拟器反馈的协助下，生成满足用户需求的高满意度响应。通过在两个TOD基准上的实证实验，我们验证了方法的有效性。结果表明，我们的方法优于先前的最先进（SOTA）结果。
英文摘要：
Dialogue systems and large language models (LLMs) have gained considerable attention. However, the direct utilization of LLMs as task-oriented dialogue (TOD) models has been found to underperform compared to smaller task-specific models. Nonetheless, it is crucial to acknowledge the significant potential of LLMs and explore improved approaches for leveraging their impressive abilities. Motivated by the goal of leveraging LLMs, we propose an alternative approach called User-Guided Response Optimization (UGRO) to combine it with a smaller TOD model. This approach uses LLM as annotation-free user simulator to assess dialogue responses, combining them with smaller fine-tuned end-to-end TOD models. By utilizing the satisfaction feedback generated by LLMs, UGRO further optimizes the supervised fine-tuned TOD model. Specifically, the TOD model takes the dialogue history as input and, with the assistance of the user simulator's feedback, generates high-satisfaction responses that meet the user's requirements. Through empirical experiments on two TOD benchmarks, we validate the effectiveness of our method. The results demonstrate that our approach outperforms previous state-of-the-art (SOTA) results.
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。
