arXiv cs.CL· Juan Li, Fangshu Chang, Xinyi Jiang, Ling Huang, Yunzhang Chen·· 12 小时前AI 评分29
ProfileSim：用强化学习与分层奖励驱动的用户模拟框架，面向金融营销外呼任务型对话
Profile-Driven User Simulation via Reinforcement Learning with Hierarchical Rewards for Task-Oriented Dialogues
AI 导读
ProfileSim 是面向金融营销外呼的用户模拟框架，联合建模用户画像（人口统计与 Big Five 人格特质）和从真实通话日志逆向还原的业务画像，基座模型在真实语音对话数据上微调后用 GRPO 与对话级、话语级分层奖励优化。
正文 · 原文
Abstract:Building Task-Oriented Dialogue (TOD) systems for high-value scenarios such as financial marketing requires large volumes of domain-specific dialogue data, which privacy regulations, annotation costs, and the need for expert labor make hard to obtain. User simulation offers a remedy, but existing methods target general-domain dialogue and exhibit two key limitations: insufficient modeling of domain-specific business processes and compliance constraints, and inadequate capture of the colloquial, spoken-language character of voice interactions. We propose ProfileSim, a profile-driven user simulation framework for financial marketing outbound calls. It jointly models user profiles---demographics and Big Five personality traits---and business profiles---intents reverse-engineered from real call logs---enabling fine-grained control over simulated behavior. The base model is fine-tuned on real voice dialogue data and refined by Group Relative Policy Optimization (GRPO) with hierarchical rewards at the dialogue and utterance levels. Paired with a customer service agent integrating Standard Operating Procedure (SOP) constraints and Retrieval-Augmented Generation (RAG), ProfileSim achieves the highest colloquial naturalness, the strongest user profile adherence and the lowest agent score on long-tail intents among all evaluated user generators, while producing substantially shorter user utterances at comparable business compliance. The generated dialogue data is designed to support intent recognition training, agent evaluation, and rapid cold-start deployment.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.32435 [cs.CL] |
| (or arXiv:2610.32435v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32435 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Juan Li [view email]
[v1]
Fri, 23 Oct 2026 10:01:41 UTC (1,388 KB)
来源：arXiv cs.CL · arxiv.org