Language-model groups overstate consensus when replaying human deliberation on a reasoning task
arXiv:2609.20543v1 Announce Type: new 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…
Read the full story at arXiv cs.AI ↗
ImpactNotable 31/100
Why it mattersRule-based estimate: event keywords (+4); trust 6/10.
RegionsGlobal
Published1 d ago (Fri, 18 Sep 2026 04:00:00 GMT)
RetrievedFri, 18 Sep 2026 08:00:48 GMT via rss
ClassifiedFri, 18 Sep 2026 08:01:04 GMT by heuristic
AuthorTengfei Shao