Real-Time Group Dynamics with LLM Facilitation: Evidence from a Charity Allocation Task

TL;DR

This study empirically examines how large language models (LLMs) facilitate real-time group decision-making in charity allocation tasks, revealing that while participants prefer facilitation, it can influence outcomes and perceptions without improving consensus or participation equity.

Contribution

It provides the first empirical evidence on LLM facilitation effects in group deliberation, highlighting potential governance risks like algorithmic steering and perceived inclusivity.

Findings

LLM facilitation did not significantly improve group consensus.

Facilitators shifted charity allocations by up to 5.5 percentage points.

Participants preferred facilitated discussions despite unchanged participation equity.

Abstract

As large language models (LLMs) evolve from single-user assistants to active participants in civic and workplace deliberation, evaluating their effects on collective decision making becomes a governance challenge. We present two empirical studies (N=879) of real-time, text-based group deliberation in an incentive-compatible charity allocation task with real financial stakes ($7,200 USD). Groups of three allocate a donation budget under varying LLM facilitation conditions: Study 1 (N=204) compares three frontier models; Study 2 (N=675) compares facilitator strategies against a no-facilitation baseline. Across both studies, LLM facilitation did not significantly improve group consensus in either study, yet participants consistently preferred facilitated discussion. We additionally identify two governance-relevant risks. First, algorithmic steering: facilitators shifted select charity-level allocations by up to 5.5 percentage points -- directly affecting the final charitable payout -- even when aggregate agreement metrics remained unchanged. Second, an illusion of inclusion: participants cited inclusivity as their primary reason for preferring LLM facilitators, yet neither survey nor transcript-based measures of participation equity improved. Notably, participants reported greater trust in the process under the same conditions where facilitators exerted directional influence on outcomes. Together, these findings show that in AI-mediated group deliberation, perceived procedural improvement can coexist with measurable steering and unchanged participation inequality, motivating evaluation practices that treat collective outcomes, interaction dynamics, and participant perceptions as distinct governance targets.