pith. sign in
Pith Number

pith:TK4LO3NG

pith:2026:TK4LO3NGWX5J6VA5JY2AYQGUBP
not attested not anchored not stored refs resolved

Edit-level Majority Voting Mitigates Over-Correction in LLM-based Grammatical Error Correction

Takumi Goto, Taro Watanabe, Yusuke Sakai

Edit-level majority voting over multiple LLM candidates reduces over-correction in grammatical error correction.

arxiv:2605.13624 v1 · 2026-05-13 · cs.CL

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{TK4LO3NGWX5J6VA5JY2AYQGUBP}

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

Across nine benchmarks covering English, Czech, German, Ukrainian, Korean, Hindi, and Romanian, the proposed method outperforms both greedy and MBR decoding in most cases. Moreover, it yields stable correction quality regardless of the instruction prompts used.

C2weakest assumption

That generating multiple candidates from a single LLM and applying majority voting at the edit level will reliably mitigate over-correction, assuming sufficient diversity among candidates and a well-defined notion of individual edits.

C3one line summary

Edit-level majority voting on multiple LLM-generated candidates reduces over-correction in grammatical error correction and outperforms greedy and MBR decoding on nine multilingual benchmarks while remaining stable to prompt variations.

References

61 extracted · 61 resolved · 5 Pith anchors

[1] Abhijeet Awasthi, Sunita Sarawagi, Rasna Goyal, Sabyasachi Ghosh, and Vihari Piratla. 2019. https://doi.org/10.18653/v1/D19-1435 Parallel iterative edit models for local sequence transduction . In Pro 2019 · doi:10.18653/v1/d19-1435
[2] Adriane Boyd. 2018. https://doi.org/10.18653/v1/W18-6111 Using W ikipedia edits in low resource grammatical error correction . In Proceedings of the 2018 EMNLP Workshop W- NUT : The 4th Workshop on No 2018 · doi:10.18653/v1/w18-6111
[3] In: Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications 2019 · doi:10.18653/v1/w19-4406
[4] Christopher Bryant, Mariano Felice, and Ted Briscoe. 2017. https://doi.org/10.18653/v1/P17-1074 Automatic annotation and evaluation of error types for grammatical error correction . In Proceedings of 2017 · doi:10.18653/v1/p17-1074
[5] Bin Cao, Kai Jiang, Fayu Pan, Chenlei Bao, and Jing Fan. 2024. https://aclanthology.org/2024.lrec-main.772/ Improving grammatical error correction by correction acceptability discrimination . In Proce 2024
Receipt and verification
First computed 2026-05-18T02:44:17.841674Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

9ab8b76da6b5fa9f541d4e340c40d40bdbbc0a78bf8f8e2129aebb6cc19ff358

Aliases

arxiv: 2605.13624 · arxiv_version: 2605.13624v1 · doi: 10.48550/arxiv.2605.13624 · pith_short_12: TK4LO3NGWX5J · pith_short_16: TK4LO3NGWX5J6VA5 · pith_short_8: TK4LO3NG
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/TK4LO3NGWX5J6VA5JY2AYQGUBP \
  | 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: 9ab8b76da6b5fa9f541d4e340c40d40bdbbc0a78bf8f8e2129aebb6cc19ff358
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "48e1f9ac67988d091c2669cc306f4528c6ac1f3d1076171e3f288b1e22fb06ef",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-13T14:52:15Z",
    "title_canon_sha256": "61f8de49c2e00490fb4934f8208abb32b14da80a7bfce437216991120b0d12d4"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13624",
    "kind": "arxiv",
    "version": 1
  }
}