用带角色标签的议事数据训练大模型，让虚拟议员更像真人的行为。
Point of Order: Action-Aware LLM Persona Modeling for Data-Grounded Civic Deliberation
- 将公开会议录音转为带身份标签的文本，添加动作标记和人物档案
- 模型在真实数据上微调后，角色一致性提升2倍，投票尝试增加3.6倍
- 生成内容难辨真假，适合做公民议事的可重复模拟研究
基于大模型的议事模拟能实现对公共讨论的受控研究，但现有系统缺乏说话人归属数据，且缺少对长期制度行为的评估方法。语音识别转录通常使用如$Speaker_1$的匿名标签，导致模型无法学习参与者在多轮会议中的稳定行为。本文提出一个可复现的流程，将公开的Zoom会议记录转化为带说话人归属的转录文本，并附加人物画像、议题信息与实用的“动作标签”（如$[propose_motion]$）。基于此流程，我们发布了三个政府议事公开数据集（上诉法院听证会、学区委员会会议、市政议会会议），并在这些带有动作感知的数据上微调大模型角色。评估涵盖四个维度：角色真实性、角色一致性、制度真实性与行为连贯性。结果显示，动作感知微调使困惑度降低67%，分类器评估的角色真实性翻倍，投票尝试最多提升3.6倍，议事响应能力最高提升70%。人类评估表明，模拟片段常难以与真实议事区分，证明其具备开展数据驱动型公民议事研究的实用基础。
原文摘要 · Abstract (English)
LLM-based simulations can enable controlled studies of civic deliberation, but current systems lack speaker-attributed data and methods for evaluating long-form institutional behavior. ASR transcripts typically use anonymous labels such as $Speaker\_1$, preventing models from learning stable participant behavior across meetings. We present a reproducible pipeline that converts public Zoom recordings into speaker-attributed transcripts enriched with persona profiles, topics, and pragmatic "action tags" such as $[propose\_motion]$. Using this pipeline, we release three public datasets of government deliberation (Appellate Court hearings, School Board meetings, and Municipal Council sessions) and fine-tune LLM personas on this action-aware data. We evaluate simulations along four dimensions: persona fidelity, persona consistency, institutional fidelity, and behavioral coherence. Action-aware fine-tuning cuts perplexity by 67%, doubles classifier-based persona fidelity, increases vote attempts by up to $3.6\times$, and improves deliberative responsiveness by up to 70%. Human evaluations show that simulated excerpts are often hard to distinguish from real deliberations, indicating a practical foundation for data-grounded civic simulation studies.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。