pith. machine review for the scientific record.
sign in
Pith Number

pith:INHJO2QC

pith:2026:INHJO2QCMVHFQHOVNJSA6VMERY
not attested not anchored not stored refs resolved

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

Aaron Parisi, Alden Hallak, Crystal Qian, Nithum Thain, Vivian Tsai

LLM facilitators in group charity tasks shift specific donation shares by up to 5.5 points without raising overall consensus or participation equity.

arxiv:2605.14097 v1 · 2026-05-13 · cs.HC

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open
Portable graph bundle live · download bundle · merged state
The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

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.

C2weakest assumption

That the specific charity allocation task with real financial stakes and text-only chat generalizes to other group deliberation settings, and that the chosen survey and transcript metrics adequately capture steering and equity effects without missing subtle dynamics.

C3one line summary

LLM facilitators in real-stakes group charity decisions shift specific allocations without raising consensus or participation equity, yet increase perceived trust and preference for the process.

References

62 extracted · 62 resolved · 2 Pith anchors

[1] Mohammed Alsobay, David M Rothschild, Jake M Hofman, and Daniel G Goldstein. 2025. Bringing Everyone to the Table: An Experimental Study of LLM-Facilitated Group Decision Making.arXiv preprint arXiv:2 2025
[2] Constitutional AI: Harmlessness from AI Feedback 2022 · arXiv:2212.08073
[3] Communication-aware robotics: Exploiting motion for communication 2020 · doi:10.1146/annurev-
[4] Using thematic analysis in psychology 2006 · doi:10.1191/1478088706qp063oa
[5] Gajos, and Elena L 2020 · doi:10.1145/3377325.3377498
Receipt and verification
First computed 2026-05-17T23:39:12.140250Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

434e976a02654e581dd56a640f55848e16d6e4393c2e8510a969a724699a3b1a

Aliases

arxiv: 2605.14097 · arxiv_version: 2605.14097v1 · doi: 10.48550/arxiv.2605.14097 · pith_short_12: INHJO2QCMVHF · pith_short_16: INHJO2QCMVHFQHOV · pith_short_8: INHJO2QC
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/INHJO2QCMVHFQHOVNJSA6VMERY \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 434e976a02654e581dd56a640f55848e16d6e4393c2e8510a969a724699a3b1a
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "4cb4ee6167eca055b20e1c1d195d971e4818b7b21a1fb0f9553b169b80d54e78",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.HC",
    "submitted_at": "2026-05-13T20:28:21Z",
    "title_canon_sha256": "694dc2a5dd6a60962b7ae817fc71d38d0f0ae1e103b26a3b5bbc6837e3aca914"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14097",
    "kind": "arxiv",
    "version": 1
  }
}