发表机构
Doctoral School of Mathematics, Computer Science and Telecommunications of Toulouse（图卢兹数学、计算机科学与电信博士学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究探讨基于大型语言模型的数字孪生在增强民主中的机遇与挑战，涵盖个人偏好预测、组织集体表征及对抗攻击的鲁棒性，强调准确表征与忠实聚合。
AI 中文摘要
人工智能使计算代理能够代表政治偏好并参与集体决策。在本论文中，我研究了基于大型语言模型（LLMs）的数字孪生（DTs）作为增强民主中中介的机遇与挑战，重点关注个人偏好表征、政治组织的集体表征，以及这些表征对攻击者的脆弱性。首先，利用巴西一项在线实验的数据，我检验了个性化数字孪生能否预测公民对未见政策提案的偏好。其次，我将数字孪生框架从个人扩展到政治组织。利用瑞士议会数据，我从立法者的立法记录中构建了主题特定的知识图谱，并将其连接到基于LLM的立法者代理，这些代理被组织成代表集体立场的政党级数字孪生。这些代理之间的代理性审议测试了聚合的政党表征是否比官方政党通讯更能捕捉党内多元视角。最后，我研究了LLM中介的审议对提示注入攻击的脆弱性和鲁棒性，这些攻击会放大观点、压制意见或转移共识。利用2023年英国一项审议实验的数据，我分析了攻击效果如何随意见分布和修辞策略而变化，并评估了一个结合注入检测、结构化意见表征和强化学习的管道以提高抵抗力。这些发现刻画了基于LLM的数字孪生在增强民主中的机遇与挑战，强调了准确的偏好表征、忠实的聚合以及对战略互动的鲁棒性。
英文摘要
Artificial intelligence enables computational agents to represent political preferences and take part in collective decision-making. In this thesis, I investigate the opportunities and challenges of digital twins (DTs) based on Large Language Models (LLMs) as intermediaries in augmented democracy, focusing on individual preference representation, collective representation of political organizations, and the vulnerability of those representations to attackers. First, using data from an online experiment in Brazil, I examine whether personalized DTs can predict citizens' preferences for unseen policy proposals. Second, I extend the DT framework from individuals to political organizations. Using Swiss parliamentary data, I build topic-specific knowledge graphs from lawmakers' legislative records and connect them to LLM-based lawmaker agents, which are organized into party-level DTs representing collective positions. Agentic deliberation among these agents tests whether aggregated party representations capture a broader range of intra-party perspectives than official party communications. Finally, I study the vulnerability and robustness of LLM-mediated deliberation against prompt-injection attacks that amplify viewpoints, suppress opinions, or redirect consensus. Using data from a 2023 deliberative experiment in the United Kingdom, I analyze how attack effectiveness varies with the distribution of opinions and rhetorical strategies, and evaluate a pipeline combining injection detection, structured opinion representations, and reinforcement learning to improve resistance. These findings characterize the opportunities and challenges of LLM-based digital twins in augmented democracy, stressing accurate preference representation, faithful aggregation, and robustness to strategic interaction.
CommentsPhD thesis, Center for Collective Learning (Toulouse School of Economics), 2026. 149 pages, 28 figures
