The Empty Chair: Using LLMs to Raise Missing Perspectives in Policy Deliberations

2025-03-18

AI Summary

Policy deliberation frequently suffers from underrepresentation of marginalized groups due to physical, economic, and social barriers—eroding democratic legitimacy and exacerbating polarization. To address this, we propose an LLM-driven “Absent Stakeholder Personification Agent” system that, in real-world citizen assemblies, performs real-time speech transcription, detects perspective gaps, and generates identity-aware, context-sensitive interventions via role-informed prompting. Deployed in a sustainable development citizens’ assembly (N=19), it is the first AI-augmented deliberative tool empirically validated for actively bridging participation gaps in situ. Results demonstrate its capacity to surface novel议题 and reintroduce systematically overlooked positions; yet it also exposes critical challenges—including response generalization and overreliance on user trust. The work advances both technical innovation (a real-time speech–role–response co-adaptive architecture) and humanistic reflection, offering an empirically grounded pathway—and clear boundary conditions—for AI-enabled inclusive democracy.

Technology Category

• Humans and AI: Voting
• Multiagent Systems: Agreement, Argumentation & Negotiation
• Philosophy and Ethics of AI: Bias, Fairness & Equity

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

Deliberation is essential to well-functioning democracies, yet physical, economic, and social barriers often exclude certain groups, reducing representativeness and contributing to issues like group polarization. In this work, we explore the use of large language model (LLM) personas to introduce missing perspectives in policy deliberations. We develop and evaluate a tool that transcribes conversations in real-time and simulates input from relevant but absent stakeholders. We deploy this tool in a 19-person student citizens' assembly on campus sustainability. Participants and facilitators found that the tool sparked new discussions and surfaced valuable perspectives they had not previously considered. However, they also noted that AI-generated responses were sometimes overly general. They raised concerns about overreliance on AI for perspective-taking. Our findings highlight both the promise and potential risks of using LLMs to raise missing points of view in group deliberation settings.

Problem

• Exclusion of groups in policy deliberations due to barriers
• Use of LLMs to simulate missing stakeholder perspectives
• Evaluation of AI's role in enhancing group discussions

Innovation

• LLMs simulate missing stakeholder perspectives
• Real-time transcription and AI input generation
• Deployed in campus sustainability assembly