pith. sign in
Pith Number

pith:SQ4IF5TY

pith:2026:SQ4IF5TY3BRGKD6F5BMVSVN2P4
not attested not anchored not stored refs pending

Post-Training Language Models for Crosslingual Consistency

Arianna Bisazza, Jirui Qi, Mrinmaya Sachan, Raquel Fern\'andez, Ryan Cotterell, Tianyu Liu

Direct Consistency Optimization derives a reward from the LLM itself to produce consistent answers to the same question across languages.

arxiv:2603.04678 v3 · 2026-03-04 · cs.CL · cs.AI

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{SQ4IF5TY3BRGKD6F5BMVSVN2P4}

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

DCO significantly improves crosslingual consistency across diverse LLMs and outperforms existing methods when training with samples of multiple languages, while complementing DPO when gold labels are available.

C2weakest assumption

That a structured reward function derived directly from the LLM itself can reliably enforce true crosslingual knowledge consistency without introducing new inconsistencies or biases during optimization.

C3one line summary

DCO optimizes LLMs for crosslingual knowledge consistency via a structured reward derived directly from the model itself, outperforming prior methods in experiments.

Receipt and verification
First computed 2026-05-29T02:05:42.407885Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

943882f678d862650fc5e8595955ba7f3ca47bbaa704f4b6609af2855da68ed2

Aliases

arxiv: 2603.04678 · arxiv_version: 2603.04678v3 · doi: 10.48550/arxiv.2603.04678 · pith_short_12: SQ4IF5TY3BRG · pith_short_16: SQ4IF5TY3BRGKD6F · pith_short_8: SQ4IF5TY
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/SQ4IF5TY3BRGKD6F5BMVSVN2P4 \
  | 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: 943882f678d862650fc5e8595955ba7f3ca47bbaa704f4b6609af2855da68ed2
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "75c3b87e8a501f274f185f6199870b7e203119e421ae1f2b71846f8e7dc76e19",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-03-04T23:36:55Z",
    "title_canon_sha256": "09d72fb9a9527f525d87a573e62294c876568a39a6fa759e384c3ba68e37c252"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2603.04678",
    "kind": "arxiv",
    "version": 3
  }
}