Pith Number

pith:P6HZQIN2

pith:2026:P6HZQIN2QM6BUV3B27HPELY3JC

not attested not anchored not stored refs resolved

Fairness-Aware Retrieval Optimization for Retrieval-Augmented Generation

Jyrki Nummenmaa, Kostas Stefanidis, Vasilis Efthymiou, Yingqi Zhao

Retrieval optimization that models position-dependent bias propagation can reduce unfairness in RAG outputs while maintaining document relevance.

arxiv:2605.15790 v1 · 2026-05-15 · cs.DB · 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{P6HZQIN2QM6BUV3B27HPELY3JC}

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

Experimental results show that our method effectively mitigates generation bias while preserving relevance.

C2weakest assumption

The position-aware model of bias propagation combined with controlled bias injection via reranking accurately represents how retrieval choices affect downstream generation bias in top-k settings.

C3one line summary

Introduces FARO, a scalable quadratic optimization approach for fairness-aware top-k retrieval in RAG that mitigates generation bias via controlled reranking and position-aware propagation modeling.

References

37 extracted · 37 resolved · 7 Pith anchors

[1] URL:https://papers.nips.cc/paper_files/paper/ 2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html 2017

[2] Scaling Laws for Neural Language Models 2020 · arXiv:2001.08361

[3] Barret Zoph, Irwan Bello, Sameer Kumar, Nan Du, Yanping Huang, Jeff Dean, Noam Shazeer, and William Fedus 2023 · doi:10.1145/3571730

[4] P. Lewis, E. Perez, A. Piktus, F. Petroni, V. Karpukhin, N. Goyal, H. Küttler, M. Lewis, W.-t. Yih, T. Rocktäschel, S. Riedel, D. Kiela, Retrieval-augmented generation for knowledge-intensive nlp task 2020

[5] M. Hu, H. Wu, Z. Guan, R. Zhu, D. Guo, D. Qi, S. Li, No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vig- 36 ilant Users, 2024. URL:http://arxiv.org/abs/2410.07589. 2024

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:01:18.453135Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

7f8f9821ba833c1a5761d7cef22f1b48ab6a5e2e103ca6e3d9d34ffd38649c0f

Aliases

arxiv: 2605.15790 · arxiv_version: 2605.15790v1 · doi: 10.48550/arxiv.2605.15790 · pith_short_12: P6HZQIN2QM6B · pith_short_16: P6HZQIN2QM6BUV3B · pith_short_8: P6HZQIN2

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/P6HZQIN2QM6BUV3B27HPELY3JC \
  | 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: 7f8f9821ba833c1a5761d7cef22f1b48ab6a5e2e103ca6e3d9d34ffd38649c0f

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "fb9343d7b6a6fe1ca807a48de349a9bd6f1b331166f7ee75c7d6c209378ae88e",
    "cross_cats_sorted": [
      "cs.IR"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.DB",
    "submitted_at": "2026-05-15T09:47:44Z",
    "title_canon_sha256": "a36530d23550d6b31da3480d03dcb111072589ebe0d22fb7a41ea0628b7a2b55"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15790",
    "kind": "arxiv",
    "version": 1
  }
}