arXiv 2502.189682025-06-29cs.CL

先了解你再更好地成为你：基于隐式画像的类人用户模拟器建模

Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles

SRIBD, School of Data Science, The Chinese University of Hong Kong, Shenzhen, Guangdong（香港中文大学（深圳）数据科学学院）；Artificial Intelligence Research Institute, Shenzhen University of Advanced Technology（深圳先进技术大学人工智能研究院）；Department of ECE, National University of Singapore（新加坡国立大学电子工程系）

Kuang Wang, Xianfei Li, Shenghao Yang, Li Zhou, Feng Jiang, Haizhou Li

备注：: 9 pages. Accepted to ACL 2025. Camera-ready version

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出基于隐式画像的用户模拟器USP，通过LLM抽取隐式画像并结合条件监督微调与强化学习优化多层级对话模拟，显著提升了用户模拟的真实性与多样性。

摘要：

用户模拟器对于复现人与对话系统的交互至关重要，它支持大型语言模型（LLM）的协同训练和自动评估。然而，当前的角色扮演方法面临诸多挑战，如缺乏话语级真实性和用户级多样性，常受限于角色混淆和对知名人物预定义画像的依赖。相比之下，直接模拟仅关注文本，忽略了隐式用户特征，如个性和对话级一致性。为解决这些问题，我们提出了带有隐式画像的用户模拟器（USP），这是一个从人机交互中推断隐式用户画像以模拟个性化、真实对话的框架。我们首先开发了一个由 LLM 驱动的抽取器，具备全面的画像模式；随后利用条件监督微调和带有循环一致性的强化学习来优化模拟，在话语和对话两个层级上进行优化。最后，一个多样化的画像采样器捕获真实世界用户画像的分布。实验结果表明，USP 在真实性和多样性上优于强基线，同时保持相当的一致性。此外，使用 USP 在动态多轮上评估 LLM 与主流基准对齐良好，证明了其在实际应用中的有效性。

英文摘要：

User simulators are crucial for replicating human interactions with dialogue systems, supporting both collaborative training and automatic evaluation, especially for large language models (LLMs). However, current role-playing methods face challenges such as a lack of utterance-level authenticity and user-level diversity, often hindered by role confusion and dependence on predefined profiles of well-known figures. In contrast, direct simulation focuses solely on text, neglecting implicit user traits like personality and conversation-level consistency. To address these issues, we introduce the User Simulator with Implicit Profiles (USP), a framework that infers implicit user profiles from human-machine interactions to simulate personalized and realistic dialogues. We first develop an LLM-driven extractor with a comprehensive profile schema, then refine the simulation using conditional supervised fine-tuning and reinforcement learning with cycle consistency, optimizing at both the utterance and conversation levels. Finally, a diverse profile sampler captures the distribution of real-world user profiles. Experimental results show that USP outperforms strong baselines in terms of authenticity and diversity while maintaining comparable consistency. Additionally, using USP to evaluate LLM on dynamic multi-turn aligns well with mainstream benchmarks, demonstrating its effectiveness in real-world applications.

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。