pith. sign in
Pith Number

pith:KYYGKFET

pith:2026:KYYGKFET6LGLY6VBTSW6RAX545
not attested not anchored not stored refs resolved

From Descriptive to Prescriptive: Uncover the Social Value Alignment of LLM-based Agents

Jinxian Qu, Luo Ji, Qingqing Gu, Teng Chen

GraphRAG turns social value theories into retrievable instructions that steer LLM agents toward expected behaviors in dilemmas.

arxiv:2605.14034 v1 · 2026-05-13 · cs.AI · cs.CL · cs.CY

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{KYYGKFET6LGLY6VBTSW6RAX545}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

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

By experimenting with our method on the benchmark of DAILYDILEMMAS, our method exhibits significant performance gains compared to prompt-based baselines, including ECoT, Plan-and-Solve, and Metacognitive prompting. Our method provides a basis for the emergence of self-emotion in AI systems.

C2weakest assumption

That expected behaviors defined from Maslow's Hierarchy of Needs and Plutchik's Wheel of Emotion accurately represent social value alignment for LLM agents, and that GraphRAG retrieval of instructions will reliably steer agents to produce those behaviors in conversation contexts.

C3one line summary

A GraphRAG framework converts principles into value instructions for LLM agents, yielding gains over baselines on DAILYDILEMMAS by defining expected behaviors via Maslow's needs and Plutchik's emotions.

References

15 extracted · 15 resolved · 1 Pith anchors

[1] Consciousness in Artificial Intelligence: Insights from the Science of Consciousness 2024 · arXiv:2308.08708
[2] In Proceedings of the 41st International Conference on Machine Learning, ICML’24 2002
[3] Pursu- ing worthy goals and honor in a balanced manner
[4] Identify all entities. For each identified entity, extract the following information: - entity_name: Name of the entity, capitalized - entity_type: One of the following types: [entity_types] - entity_
[5] From the entities identified in step 1, identify all pairs of (source_entity, target_entity) that areclearly relatedto each other. For each pair of related entities, extract the following information:
Receipt and verification
First computed 2026-05-17T23:39:12.809442Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

5630651493f2ccbc7aa19cade882fde779cc3f57d6d2dfff4a35031303e2ac3f

Aliases

arxiv: 2605.14034 · arxiv_version: 2605.14034v1 · doi: 10.48550/arxiv.2605.14034 · pith_short_12: KYYGKFET6LGL · pith_short_16: KYYGKFET6LGLY6VB · pith_short_8: KYYGKFET
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/KYYGKFET6LGLY6VBTSW6RAX545 \
  | 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: 5630651493f2ccbc7aa19cade882fde779cc3f57d6d2dfff4a35031303e2ac3f
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "584c47edf2408aeebd5b29206ac49c75bc46783ed193340e19383358e1bf1a69",
    "cross_cats_sorted": [
      "cs.CL",
      "cs.CY"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-13T18:50:22Z",
    "title_canon_sha256": "1930e00d0c3106a6cd36b84dd71ddb46c852416afb7841efc2abc115c6cf9290"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14034",
    "kind": "arxiv",
    "version": 1
  }
}