用大模型当数字代表，帮人参与集体决策。
Language Agents as Digital Representatives in Collective Decision-Making
- 用语言模型模拟人类行为，充当个人的数字代表。
- 在共识达成任务中，微调后的模型能有效复现原用户决策结果。
- 适合研究群体决策、机制设计或想低成本替代真人参与的场景。
在集体决策过程中，个体通过代理者表达自身偏好，即“代表”角色。本文探讨训练语言模型作为人类代理的可能性，使其能准确体现所代表个体的偏好。首先，形式化了集体决策为一组代理与决策机制之间的交互过程；其次，定义了“数字代表”问题，即通过模拟个体行为以获得机制上的等效结果。最后，在多元人群的共识形成场景中开展实证研究，证明微调大型语言模型可作为有效的数字代表。
原文摘要 · Abstract (English)
Consider the process of collective decision-making, in which a group of individuals interactively select a preferred outcome from among a universe of alternatives. In this context, "representation" is the activity of making an individual's preferences present in the process via participation by a proxy agent -- i.e. their "representative". To this end, learned models of human behavior have the potential to fill this role, with practical implications for multi-agent scenario studies and mechanism design. In this work, we investigate the possibility of training \textit{language agents} to behave in the capacity of representatives of human agents, appropriately expressing the preferences of those individuals whom they stand for. First, we formalize the setting of \textit{collective decision-making} -- as the episodic process of interaction between a group of agents and a decision mechanism. On this basis, we then formalize the problem of \textit{digital representation} -- as the simulation of an agent's behavior to yield equivalent outcomes from the mechanism. Finally, we conduct an empirical case study in the setting of \textit{consensus-finding} among diverse humans, and demonstrate the feasibility of fine-tuning large language models to act as digital representatives.
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。