pith. machine review for the scientific record. sign in

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

Recognition: 2 theorem links

· Lean Theorem

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

Shaomu Tan , Dawei Zhu , Ke Tran , Michael Denkowski , Sony Trenous , Bill Byrne , Leonardo Ribeiro , Felix Hieber
Authors on Pith no claims yet

Pith reviewed 2026-05-14 20:05 UTC · model grok-4.3

classification 💻 cs.CL
keywords LLM refinementdocument-level translationliterary translationmachine translationself-refinementgranularity effectstranslation qualityfluency and style
0
0 comments X

The pith

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

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper tests what iterative LLM self-refinement actually changes when translating full literary documents. Across nine models, seven language pairs, and multiple granularity setups, the strongest and most stable results come from first translating the entire document and then refining it segment by segment. Gains appear mainly in fluency, style, and terminology consistency, while improvements to meaning accuracy remain smaller and less consistent. Refinement also tends to shift the output toward the refiner model's own stylistic distribution rather than repairing specific errors. A plain general prompt works better than prompts that target particular error types.

Core claim

The central claim is that, for literary translation, an initial document-level machine translation pass followed by segment-level refinement outperforms other granularity combinations and refinement strategies. Document-level refinement produces fewer edits and less reliable quality lifts. Across experiments, refinement improves fluency, style, and terminology more than adequacy, and the process projects the output toward the refiner model's distribution instead of performing targeted error correction. A simple general refinement prompt consistently beats error-specific prompting and evaluate-then-refine schemes.

What carries the argument

The document-level MT followed by segment-level refinement pipeline, which carries the argument by separating coarse context handling from fine-grained polishing.

If this is right

  • Refinement gains concentrate on fluency, style, and terminology rather than adequacy.
  • A single general refinement prompt outperforms error-specific and evaluate-then-refine variants.
  • The output after refinement moves closer to the refiner model's own distribution.
  • Document-level initial translation plus segment refinement remains stable across model strengths and language pairs.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Translation systems may benefit from deliberately separating document-scale context capture from segment-scale polishing in their inference pipelines.
  • The style-projection finding suggests current refinement has limited power for meaning-level error repair and may need external signals to target adequacy.
  • The recipe could be tested on other text domains such as technical or conversational material to check whether the granularity preference persists.

Load-bearing premise

The observed superiority of the hybrid granularity recipe and the quality dimension patterns will hold for LLMs, language pairs, and text genres outside the nine models, seven pairs, and literary texts tested.

What would settle it

A controlled replication using new LLMs or non-literary documents in which full document-level refinement produces larger and more stable gains than the document-then-segment pipeline would falsify the central recommendation.

Figures

Figures reproduced from arXiv: 2605.13368 by Bill Byrne, Dawei Zhu, Felix Hieber, Ke Tran, Leonardo Ribeiro, Michael Denkowski, Shaomu Tan, Sony Trenous.

Figure 1
Figure 1. Figure 1: Dimension-wise MQM-FSP gains under the Doc-Seg refinement configuration (step=4) on WMT24- [PITH_FULL_IMAGE:figures/full_fig_p006_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Annotation guidance for human evaluation. [PITH_FULL_IMAGE:figures/full_fig_p016_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Example of the annotation interface for human evaluation. The source document is divided into chunks. [PITH_FULL_IMAGE:figures/full_fig_p016_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Refinement trajectories from 16 sampled initial document translations produced by DeepSeek-V3. Colored [PITH_FULL_IMAGE:figures/full_fig_p017_4.png] view at source ↗
read the original abstract

Iterative self-refinement is a simple inference-time strategy for machine translation: an LLM revises its own translation over multiple inference-time passes. Yet document-scale refinement remains poorly understood: 1) which pipelines work best, 2) what quality dimensions improve, and 3) how refiners behave. In this paper, we present a systematic study of document-level literary translation, covering nine LLMs and seven language pairs. 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. Beyond granularity, A simple general refinement prompt consistently outperforms error-specific prompting and evaluate-then-refine schemes. Our large-scale human evaluation shows that refinement gains come primarily from fluency, style, and terminology, with limited and less consistent improvements in adequacy. Experiments varying model strength reveal refinement projects outputs toward the refiner's distribution rather than performing targeted error repair. These findings clarify the mechanisms and limitations of current refinement approaches.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

0 major / 2 minor

Summary. The manuscript presents a systematic empirical study of iterative self-refinement for document-level literary machine translation with LLMs. It evaluates nine LLMs across seven language pairs using nine granularity combinations and five refinement strategies, supported by large-scale human evaluation. The central claim is that document-level MT followed by segment-level refinement produces strong, stable gains (mainly in fluency, style, and terminology), while document-level refinement yields fewer edits and less reliable improvements; a simple general prompt outperforms error-specific or evaluate-then-refine variants, and refinement aligns outputs to the refiner's distribution rather than targeted error correction.

Significance. If the findings hold, the work offers clear practical guidance for LLM refinement pipelines in literary translation and illuminates the mechanisms and limits of current approaches. The broad coverage of models, languages, and strategies, together with consistent patterns from human judgments, provides a solid empirical foundation that can inform both research and deployment of inference-time MT improvements.

minor comments (2)
  1. [Abstract] Abstract: The abstract states that large-scale human evaluation was performed but does not mention statistical significance tests or inter-annotator agreement; adding one sentence on these points would strengthen the summary of the results.
  2. [§5] §5 (or equivalent results section): When reporting the nine granularity combinations, a compact summary table or clearer visual encoding of the exact MT/refinement granularity pairs would make the cross-condition comparisons easier to parse at a glance.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the positive review and recommendation for minor revision. We appreciate the recognition that our systematic study provides clear practical guidance for LLM refinement pipelines in literary translation, supported by broad coverage across models, languages, and human judgments.

read point-by-point responses

  1. Referee: The manuscript presents a systematic empirical study of iterative self-refinement for document-level literary machine translation with LLMs. It evaluates nine LLMs across seven language pairs using nine granularity combinations and five refinement strategies, supported by large-scale human evaluation. The central claim is that document-level MT followed by segment-level refinement produces strong, stable gains (mainly in fluency, style, and terminology), while document-level refinement yields fewer edits and less reliable improvements; a simple general prompt outperforms error-specific or evaluate-then-refine variants, and refinement aligns outputs to the refiner's distribution rather than targeted error correction.

    Authors: We thank the referee for this accurate summary of our work. The description aligns closely with our abstract, experimental design, and conclusions. No revisions are required on this point. revision: no

Circularity Check

0 steps flagged

No significant circularity

full rationale

This is a purely empirical study that reports results from systematic experiments across nine LLMs, seven language pairs, multiple granularity combinations, refinement strategies, and large-scale human evaluations. The central claims rest on direct comparisons of observed outcomes (e.g., document-level MT + segment-level refinement vs. document-level refinement) without any mathematical derivations, equations, parameter fitting, or self-referential definitions. No load-bearing step reduces to its own inputs by construction, and the findings are externally falsifiable via the reported experimental setup.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The study depends on standard domain assumptions in NLP evaluation rather than introducing new free parameters or entities.

axioms (1)
  • domain assumption Human judgments reliably measure improvements in translation quality dimensions such as fluency, style, terminology, and adequacy.
    The conclusions about what refinement improves rely on the validity of the human evaluation protocol.

pith-pipeline@v0.9.0 · 5509 in / 1184 out tokens · 38377 ms · 2026-05-14T20:05:46.245306+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

39 extracted references · 39 canonical work pages · 5 internal anchors

  1. [1]

    Ademuyiwa, Andrew Caines, and Dietrich Klakow

    Jesujoba Oluwadara Alabi, Israel Abebe Azime, Miaoran Zhang, Cristina Espa \ n a-Bonet, Rachel Bawden, Dawei Zhu, David Ifeoluwa Adelani, Clement Oyeleke Odoje, Idris Akinade, Iffat Maab, Davis David, Shamsuddeen Hassan Muhammad, Neo Putini, David O. Ademuyiwa, Andrew Caines, and Dietrich Klakow. 2025. https://doi.org/10.18653/v1/2025.emnlp-main.1413 AFRI...

    work page doi:10.18653/v1/2025.emnlp-main.1413 2025

  2. [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 . Preprint, arXiv:2506.07583

    work page arXiv 2025

  3. [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 Proceedings of the Ninth Conference on Machine Translation, pages 1301--1317

    work page 2024

  4. [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 Association for Machine Translation (Volume 1), pages 181--190

    work page 2024

  5. [5]

    DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, and 181 others. 2025 a . https://arxiv.org/abs/2501.12948 Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement ...

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  6. [6]

    DeepSeek-AI, Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, Damai Dai, Daya Guo, Dejian Yang, Deli Chen, Dongjie Ji, Erhang Li, Fangyun Lin, Fucong Dai, and 181 others. 2025 b . https://arxiv.org/abs/2412.19437 Deepseek-v3 technical report . Preprint, arXiv:2412.19437

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  7. [7]

    Tobias Domhan and Dawei Zhu. 2025. Same evaluation, more tokens: On the effect of input length for machine translation evaluation using large language models. arXiv preprint arXiv:2505.01761

    work page arXiv 2025

  8. [8]

    Bryan Eikema and Wilker Aziz. 2022. Sampling-based approximations to minimum bayes risk decoding for neural machine translation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10978--10993

    work page 2022

  9. [9]

    Markus Freitag, George Foster, David Grangier, Viresh Ratnakar, Qijun Tan, and Wolfgang Macherey. 2021. Experts, errors, and context: A large-scale study of human evaluation for machine translation. Transactions of the Association for Computational Linguistics, 9:1460--1474

    work page 2021

  10. [10]

    and Rei, Ricardo and Stigt, Daan van and Coheur, Luisa and Colombo, Pierre and Martins, Andr \'e F

    Nuno M. Guerreiro, Ricardo Rei, Daan van Stigt, Luisa Coheur, Pierre Colombo, and Andr \'e F. T. Martins. 2024. https://doi.org/10.1162/tacl_a_00683 x COMET : Transparent machine translation evaluation through fine-grained error detection . Transactions of the Association for Computational Linguistics, 12:979--995

    work page doi:10.1162/tacl_a_00683 2024

  11. [11]

    Zhiwei He, Tian Liang, Wenxiang Jiao, Zhuosheng Zhang, Yujiu Yang, Rui Wang, Zhaopeng Tu, Shuming Shi, and Xing Wang. 2024. Exploring human-like translation strategy with large language models. Transactions of the Association for Computational Linguistics, 12:229--246

    work page 2024

  12. [12]

    Hanxu Hu, Jannis Vamvas, and Rico Sennrich. 2025. https://doi.org/10.18653/v1/2025.findings-emnlp.1289 Source-primed multi-turn conversation helps large language models translate documents . In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 23702--23712, Suzhou, China. Association for Computational Linguistics

    work page doi:10.18653/v1/2025.findings-emnlp.1289 2025

  13. [13]

    Marcin Junczys-Dowmunt. 2025. https://doi.org/10.18653/v1/2025.wmt-1.67 GEMBA v2: Ten judgments are better than one . In Proceedings of the Tenth Conference on Machine Translation, pages 926--933, Suzhou, China. Association for Computational Linguistics

    work page doi:10.18653/v1/2025.wmt-1.67 2025

  14. [14]

    Ahrii Kim. 2025. https://aclanthology.org/2025.wmt-1.5 Context is ubiquitous, but rarely changes judgments: Revisiting document-level mt evaluation . In Proceedings of the Tenth Conference on Machine Translation (WMT 2025), pages 81--97, Suzhou, China. Association for Computational Linguistics

    work page 2025

  15. [15]

    Tom Kocmi, Ekaterina Artemova, Eleftherios Avramidis, Rachel Bawden, Ond r ej Bojar, Konstantin Dranch, Anton Dvorkovich, Sergey Dukanov, Mark Fishel, Markus Freitag, Thamme Gowda, Roman Grundkiewicz, Barry Haddow, Marzena Karpinska, Philipp Koehn, Howard Lakougna, Jessica Lundin, Christof Monz, Kenton Murray, and 10 others. 2025. https://doi.org/10.18653...

    work page doi:10.18653/v1/2025.wmt-1.22 2025

  16. [16]

    Tom Kocmi, Eleftherios Avramidis, Rachel Bawden, Ond r ej Bojar, Anton Dvorkovich, Christian Federmann, Mark Fishel, Markus Freitag, Thamme Gowda, Roman Grundkiewicz, and 1 others. 2024. Findings of the wmt24 general machine translation shared task: The llm era is here but mt is not solved yet. In Proceedings of the Ninth Conference on Machine Translation...

    work page 2024

  17. [17]

    Tom Kocmi and Christian Federmann. 2023. Gemba-mqm: Detecting translation quality error spans with gpt-4. In Proceedings of the Eighth Conference on Machine Translation, pages 768--775

    work page 2023

  18. [18]

    Ann Lee, Michael Auli, and Marc’Aurelio Ranzato. 2021. Discriminative reranking for neural machine translation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 7250--7264

    work page 2021

  19. [19]

    Monishwaran Maheswaran, Marco Carini, Christian Federmann, and Tony Diaz. 2025. https://doi.org/10.18653/v1/2025.wmt-1.76 TASER : Translation assessment via systematic evaluation and reasoning . In Proceedings of the Tenth Conference on Machine Translation, pages 1004--1010, Suzhou, China. Association for Computational Linguistics

    work page doi:10.18653/v1/2025.wmt-1.76 2025

  20. [20]

    Niklas Muennighoff, Zitong Yang, Weijia Shi, Xiang Lisa Li, Li Fei-Fei, Hannaneh Hajishirzi, Luke Zettlemoyer, Percy Liang, Emmanuel Candes, and Tatsunori Hashimoto. 2025. https://doi.org/10.18653/v1/2025.emnlp-main.1025 s1: Simple test-time scaling . In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 20286--2...

    work page doi:10.18653/v1/2025.emnlp-main.1025 2025

  21. [21]

    Dayy \'a n O ' Brien, Bhavitvya Malik, Ona de Gibert, Pinzhen Chen, Barry Haddow, and J \"o rg Tiedemann. 2025. https://doi.org/10.18653/v1/2025.wmt-1.17 D oc HPLT : A massively multilingual document-level translation dataset . In Proceedings of the Tenth Conference on Machine Translation, pages 286--300, Suzhou, China. Association for Computational Linguistics

    work page doi:10.18653/v1/2025.wmt-1.17 2025

  22. [22]

    gpt-oss-120b & gpt-oss-20b Model Card

    OpenAI, :, Sandhini Agarwal, Lama Ahmad, Jason Ai, Sam Altman, Andy Applebaum, Edwin Arbus, Rahul K. Arora, Yu Bai, Bowen Baker, Haiming Bao, Boaz Barak, Ally Bennett, Tyler Bertao, Nivedita Brett, Eugene Brevdo, Greg Brockman, Sebastien Bubeck, and 108 others. 2025. https://arxiv.org/abs/2508.10925 gpt-oss-120b & gpt-oss-20b model card . Preprint, arXiv:...

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  23. [23]

    Ziqian Peng, Rachel Bawden, and Fran c ois Yvon. 2025. https://aclanthology.org/2025.mtsummit-1.3/ Investigating length issues in document-level machine translation . In Proceedings of Machine Translation Summit XX: Volume 1, pages 4--23, Geneva, Switzerland. European Association for Machine Translation

    work page 2025

  24. [24]

    Qwen, :, An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, and 25 others. 2025. https://arxiv.org/abs/2412.15115 Qwen2.5 technical report . Preprint, arXiv:2412.15115

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  25. [25]

    Miguel Moura Ramos, Patrick Fernandes, Sweta Agrawal, and Andre Martins. 2025. https://openreview.net/forum?id=Ah0U1r5Ldq Multilingual contextualization of large language models for document-level machine translation . In Second Conference on Language Modeling

    work page 2025

  26. [26]

    Ricardo Rei, Jos \'e G. C. de Souza, Duarte Alves, Chrysoula Zerva, Ana C Farinha, Taisiya Glushkova, Alon Lavie, Luisa Coheur, and Andr \'e F. T. Martins. 2022. https://aclanthology.org/2022.wmt-1.52/ COMET -22: Unbabel- IST 2022 submission for the metrics shared task . In Proceedings of the Seventh Conference on Machine Translation (WMT), pages 578--585...

    work page 2022

  27. [27]

    Kirill Semenov, Xu Huang, Vil \'e m Zouhar, Nathaniel Berger, Dawei Zhu, Arturo Oncevay, and Pinzhen Chen. 2025. https://doi.org/10.18653/v1/2025.wmt-1.30 Findings of the WMT 25 terminology translation task: Terminology is useful especially for good MT s . In Proceedings of the Tenth Conference on Machine Translation, pages 554--576, Suzhou, China. Associ...

    work page doi:10.18653/v1/2025.wmt-1.30 2025

  28. [28]

    Yirong Sun, Dawei Zhu, Yanjun Chen, Erjia Xiao, Xinghao Chen, and Xiaoyu Shen. 2025. https://doi.org/10.18653/v1/2025.naacl-srw.1 Fine-grained and multi-dimensional metrics for document-level machine translation . In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language T...

    work page doi:10.18653/v1/2025.naacl-srw.1 2025

  29. [29]

    Shaomu Tan, Ryosuke Mitani, Ritvik Choudhary, and Toshiyuki Sekiya. 2025 a . https://arxiv.org/abs/2509.19020 Investigating test-time scaling with reranking for machine translation . arXiv preprint arXiv:2509.19020

    work page arXiv 2025

  30. [30]

    Shaomu Tan, Ryosuke Mitani, Ritvik Choudhary, Qiyu Wu, Toshiyuki Sekiya, and Christof Monz. 2025 b . https://arxiv.org/abs/2512.18906 Remedy-r: Generative reasoning for machine translation evaluation without error annotations . Preprint, arXiv:2512.18906

    work page arXiv 2025

  31. [31]

    Shaomu Tan and Christof Monz. 2025. https://doi.org/10.18653/v1/2025.emnlp-main.217 R e M edy: Learning machine translation evaluation from human preferences with reward modeling . In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 4370--4387, Suzhou, China. Association for Computational Linguistics

    work page doi:10.18653/v1/2025.emnlp-main.217 2025

  32. [32]

    Longyue Wang, Chenyang Lyu, Tianbo Ji, Zhirui Zhang, Dian Yu, Shuming Shi, and Zhaopeng Tu. 2023. https://doi.org/10.18653/v1/2023.emnlp-main.1036 Document-level machine translation with large language models . In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 16646--16661, Singapore. Association for Computat...

    work page doi:10.18653/v1/2023.emnlp-main.1036 2023

  33. [33]

    Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, and 1 others. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35:24824--24837

    work page 2022

  34. [34]

    Di Wu, Seth Aycock, and Christof Monz. 2025. Please translate again: Two simple experiments on whether human-like reasoning helps translation. arXiv preprint arXiv:2506.04521

    work page arXiv 2025

  35. [35]

    Minghao Wu, Thuy-Trang Vu, Lizhen Qu, George Foster, and Gholamreza Haffari. 2024. https://arxiv.org/abs/2401.06468 Adapting large language models for document-level machine translation . Preprint, arXiv:2401.06468

    work page arXiv 2024

  36. [36]

    Wenda Xu, Daniel Deutsch, Mara Finkelstein, Juraj Juraska, Biao Zhang, Zhongtao Liu, William Yang Wang, Lei Li, and Markus Freitag. 2024. Llmrefine: Pinpointing and refining large language models via fine-grained actionable feedback. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 1429--1445

    work page 2024

  37. [37]

    An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, and 41 others. 2025. https://arxiv.org/abs/2505.09388 Qwen3 technical report . Preprint, arXiv:2505.09388

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  38. [38]

    Yu Zhao, Huifeng Yin, Bo Zeng, Hao Wang, Tianqi Shi, Chenyang Lyu, Longyue Wang, Weihua Luo, and Kaifu Zhang. 2024. Marco-o1: Towards open reasoning models for open-ended solutions. arXiv preprint arXiv:2411.14405

    work page arXiv 2024

  39. [39]

    Gonzalez, Clark Barrett, and Ying Sheng

    Lianmin Zheng, Liangsheng Yin, Zhiqiang Xie, Chuyue Sun, Jeff Huang, Cody Hao Yu, Shiyi Cao, Christos Kozyrakis, Ion Stoica, Joseph E. Gonzalez, Clark Barrett, and Ying Sheng. 2024. https://doi.org/10.52202/079017-2000 Sglang: Efficient execution of structured language model programs . In Advances in Neural Information Processing Systems, volume 37, pages...

    work page doi:10.52202/079017-2000 2024