Language Agents as Digital Representatives in Collective Decision-Making

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 $\mathit{\text{language}}\mathit{\text{agents}}$ 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 $\mathit{\text{collective}}\mathit{\text{decision-making}}$ – as the episodic process of interaction between a group of agents and a decision mechanism. On this basis, we then formalize the problem of $\mathit{\text{digital}}\mathit{\text{representation}}$ – 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 $\mathit{\text{consensus-finding}}$ among diverse humans, and demonstrate the feasibility of fine-tuning large language models to act as digital representatives.