Pith Number

pith:DAH7FRMB

pith:2024:DAH7FRMBQC27SO7NE7UE224JKT

not attested not anchored not stored refs resolved

A Roadmap to Pluralistic Alignment

Andre Ye, Christopher Michael Rytting, Jared Moore, Jillian Fisher, Liwei Jiang, Mitchell Gordon, Niloofar Mireshghallah, Nouha Dziri, Taylor Sorensen, Tim Althoff, Ximing Lu, Yejin Choi

Standard alignment procedures may reduce distributional pluralism in language models.

arxiv:2402.05070 v3 · 2024-02-07 · cs.AI · cs.CL · cs.IR

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{DAH7FRMBQC27SO7NE7UE224JKT}

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

standard alignment procedures might reduce distributional pluralism in models

C2weakest assumption

That the three proposed definitions and benchmark classes are sufficient to operationalize and measure pluralism without missing key aspects of value diversity or introducing new biases in the measurement process itself.

C3one line summary

The paper formalizes three types of pluralistic AI models and three benchmark classes, arguing that current alignment techniques may reduce rather than increase distributional pluralism.

References

282 extracted · 282 resolved · 19 Pith anchors

[2] J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F 2023

[3] Aher, G. V., Arriaga, R. I., and Kalai, A. T. Using large language models to simulate multiple humans and replicate human subject studies. In International Conference on Machine Learning, pp.\ 337--37 2023

[4] Anthropic. Introducing claude, 2023. URL https://www.anthropic.com/index/introducing-claude 2023

[5] Flexible Coding of in-depth Interviews: A Twenty- rst Century Approach 2023 · doi:10.1017/pan.2023.2

[7] S., Diaz, M., Homan, C 2023

Formal links

3 machine-checked theorem links

Cited by

22 papers in Pith

Evaluating AI-Generated Images of Cultural Artifacts with Community-Informed Rubrics

Training-Free Cultural Alignment of Large Language Models via Persona Disagreement

The Algorithmic Gaze of Image Quality Assessment: An Audit and Trace Ethnography of the LAION-Aesthetics Predictor

RLHF May Not Reflect Genuine Preferences

Language Model Goal Selection Differs from Humans' in a Self-Directed Learning Task

Receipt and verification

First computed	2026-05-17T23:38:47.575175Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

180ff2c58180b5f93bed27e84d6b8954ee8bf58115932da393905ce5575b71e8

Aliases

arxiv: 2402.05070 · arxiv_version: 2402.05070v3 · doi: 10.48550/arxiv.2402.05070 · pith_short_12: DAH7FRMBQC27 · pith_short_16: DAH7FRMBQC27SO7N · pith_short_8: DAH7FRMB

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/DAH7FRMBQC27SO7NE7UE224JKT \
  | 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: 180ff2c58180b5f93bed27e84d6b8954ee8bf58115932da393905ce5575b71e8

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "0328454a2db8064d11d24c8c988f38f26a5e4167490429457d58bffc00fc88a9",
    "cross_cats_sorted": [
      "cs.CL",
      "cs.IR"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2024-02-07T18:21:17Z",
    "title_canon_sha256": "6732e70493a9192aaefe3ee7706537d31f2a80cc7baff5b2e74a99b7d5ff083a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2402.05070",
    "kind": "arxiv",
    "version": 3
  }
}