Searcharxiv⌕ Search

arXiv · 2611.19652

LLM Facilitation of Group Decision-Making

Abstract

Human groups often fail to integrate information distributed across their members, converging on incorrect decisions. We ask whether large language models (LLMs) can help groups reach the correct decision in such settings. In an online, chat-based experiment, 138 three-person groups (N = 414) completed a hidden-profile hiring task that required selecting the best candidate using public information available to all group members and private information available only to individual members. The randomized human-subject experiment included three conditions: no facilitation, an individual-level LLM that messaged each member privately, and a group-level LLM that messaged the whole group. The LLM facilitation consisted of adaptive interventions that summarized the discussion, nudged quiet members, and played devil's advocate. The LLM did not know which candidate was correct. Both LLM conditions significantly increased the rate at which groups reached consensus on the correct candidate, from 32.6% without facilitation to 56.5% with LLM facilitation. LLM-facilitated groups exchanged more consensus messages signaling agreement on the group's choice. Participants in the group-level condition also disclosed significantly more information about the correct candidate, whereas those receiving individual-level facilitation repeated public information less often. Finally, group-level facilitation received more favorable usability ratings than individual-level facilitation. These results show that LLMs can deliver adaptive, theory-informed interventions that improve group decision-making, and that the design of these interventions may shape how people respond to them.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

José Córdova, Chun-Wei Chiang, Miriam Schirmer, Ming Yin, Emőke-Ágnes Horvát. 2026-11-14. LLM Facilitation of Group Decision-Making. https://searcharxiv.com/abs/2611.19652

Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.

KEEP EXPLORING

Related papers

Human-AI Writing as Distributed Cognition: Reassessing Collaborative Writing Theories in the Age of LLMs

In this paper, we conduct a structured synthesis of existing theories and frameworks on human-human collaborative writing to assess how co-writing with AI reshapes writing in knowledge work settings, and draw seven insights along with design implications for human-AI collaborative writing tools. Our main argument is that, as we delegate more writing to AI, our cognitive process shifts from the traditional plan/write/review process to a plan/delegate/review process, reshaping the distribution of the cognitive labor between human writers and AI writing tools. To ensure that humans cognitively stay in the loop, we discuss a ``prototyping'' approach, where the writing tool scaffolds a healthier distribution of cognition through rapid, small-scale iterations that keep writers mentally in the loop even when generation is delegated to AI. We aim to bring theoretical grounding and practical guidance to the interaction designs of human-AI collaborative writing, with the goal of balancing automation with cognitive integrity.

cs.HC↗

Shielded Trajectory Sampling for Personalized Relational Safety in Conversational AI

Anthropomorphic conversational systems can provide companionship and emotional support, but repeated, seemingly harmless interactions can encourage excessive dependence and reduced human contact. We formulate safety in user-AI relationships as a sequential decision problem, using conversational cues to track the relationship and selecting responses according to their anticipated effects over time. A conditional Generative Flow Network learns from sampled response plans to select replies that preserve the largest estimated mass of safe and useful continuations. Model-based checks screen plans during training and responses during interaction, requiring at least one sequence of future response strategies that meets a prescribed safety bound under every candidate user model, independently of the learned network. Strategies are selected directly from learned first-step probabilities, avoiding online plan sampling. We evaluate the approach in simulation against reactive safeguards, filters with and without memory, and alternative planners, using exact computation to validate the learned approximation. We also evaluate relational cue extraction from real user messages in WildChat. To our knowledge, this is the first approach to select conversational replies by anticipating their effects on the user-AI relationship while imposing an explicit model-based safety bound on future response sequences. Results show close agreement with exact planning, lower decision costs at longer horizons, and improved safety-utility trade-offs when protective responses are less effective. The approach balances immediate support with the longer-term effects of repeated interaction. The source code is available at https://github.com/benedettapicano/ANTHROPOMORPHIC_SAFETY_TRAJ.

cs.HC↗

Projected Route Cues for Bouldering: Effects of Circular, Linear, and Combined Highlighting on Route Observation and Climbing

Before attempting a bouldering problem, climbers inspect the route to find its holds and plan their moves, which novices find difficult on walls where many routes overlap. We built a projector-camera system that projects route cues onto the wall and compared three cues: circles on the route holds, limb-colored lines connecting the holds, and both combined. Ninety-six participants, 61 of them first-time climbers, each climbed four routes, one per cue and one without projection, in a Latin-square order. In mixed-effects models, all three cues shortened the time before the first attempt; with circles, its geometric mean fell from 83 s to 39 s. Circles also increased the number of moves made within each trial. Lines led to more use of off-route holds than circles, mainly on routes where such holds lay under the projected lines. Participants preferred the combined cue, although no behavioral advantage of it over circles was detected.

cs.HC↗