Pith Number

pith:NXG3YUB6

pith:2026:NXG3YUB63DWKQRSY6GSLMD7BBZ

not attested not anchored not stored refs resolved

What Does LLM Refinement Actually Improve? A Systematic Study on Document-Level Literary Translation

Bill Byrne, Dawei Zhu, Felix Hieber, Ke Tran, Leonardo Ribeiro, Michael Denkowski, Shaomu Tan, Sony Trenous

Document-level translation followed by segment-level refinement produces the most reliable gains in literary machine translation.

arxiv:2605.13368 v1 · 2026-05-13 · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{NXG3YUB63DWKQRSY6GSLMD7BBZ}

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 translation-refinement granularity combinations and five refinement strategies, we find a robust recipe: document-level MT followed by segment-level refinement yields strong and stable improvements. In contrast, document-level refinement often makes fewer edits and leads to smaller or less reliable gains.

C2weakest assumption

The assumption that the observed patterns in refinement behavior and quality dimensions will generalize beyond the specific nine LLMs, seven language pairs, and literary texts tested in the study.

C3one line summary

Document-level machine translation followed by segment-level LLM refinement provides the strongest and most stable improvements in literary translation quality, mainly enhancing fluency and style rather than adequacy.

References

39 extracted · 39 resolved · 5 Pith anchors

[1] Ademuyiwa, Andrew Caines, and Dietrich Klakow 2025 · doi:10.18653/v1/2025.emnlp-main.1413

[2] Ramakrishna Appicharla, Baban Gain, Santanu Pal, and Asif Ekbal. 2025. https://arxiv.org/abs/2506.07583 Beyond the sentence: A survey on context-aware machine translation with large language models . 2025

[3] Eleftheria Briakou, Jiaming Luo, Colin Cherry, and Markus Freitag. 2024. Translating step-by-step: Decomposing the translation process for improved translation quality of long-form texts. In Proceedin 2024

[4] Pinzhen Chen, Zhicheng Guo, Barry Haddow, and Kenneth Heafield. 2024. Iterative translation refinement with large language models. In Proceedings of the 25th Annual Conference of the European Associat 2024

[5] DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning 2025 · arXiv:2501.12948

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T02:44:48.028504Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

6dcdbc503ed8eca84658f1a4b60fe10e4385a11635867779f50e2eb315dd9d0f

Aliases

arxiv: 2605.13368 · arxiv_version: 2605.13368v1 · doi: 10.48550/arxiv.2605.13368 · pith_short_12: NXG3YUB63DWK · pith_short_16: NXG3YUB63DWKQRSY · pith_short_8: NXG3YUB6

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/NXG3YUB63DWKQRSY6GSLMD7BBZ \
  | 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: 6dcdbc503ed8eca84658f1a4b60fe10e4385a11635867779f50e2eb315dd9d0f

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "e73be54613a7714e9038f97eb3d2f8c92d91c21ebfcb89d540e737cc39d30ba1",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-13T11:27:32Z",
    "title_canon_sha256": "7fba05e92e83f58cdca23df1e608365ebbd229b69ac5c092d3a21d155f305bb5"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13368",
    "kind": "arxiv",
    "version": 1
  }
}