Language-model groups overstate consensus when replaying human deliberation on a reasoning task

Paper recorded by Signals 4 on 2026-09-17 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-17 on arXiv · recorded by Signals 4 on 2026-09-18

Category: cs.CL · 自然语言处理 · first seen 2026-09-18

Abstract

Full-consensus rates are often treated as indicators of collective cognition, yet depend on how participation and final states are operationalized. We replayed 100 held-out human Wason groups with matched large language model (LLM) agent groups, seeding one belief-anchored agent per participant's pre-discussion answer and scoring agents and people with the same code. Across human scoring definitio

Read on arXiv →