---
title: "HTMR — paper by Luo et al. (2026) — summary and ideas"
description: "The authors propose HTMR, a two-stage post-training recipe: Warm-up: supervised training on chain-of-thought… 35 references."
authors: ["Jianwen Luo", "Yongkang Jin", "Yu Hong", "Jianmin Yao"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.910/"
doi: "10.18653/v1/2026.acl-long.910"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/luo-2026-htmr-hybrid-token-masking-reinforcement/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/luo-2026-htmr-hybrid-token-masking-reinforcement/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/32/) / HTMR: Hybrid Token Masking Reinforcement Learning with Verifiable Rewards for Event Argument Extraction with Multi-Perspective Reasoning

# HTMR: Hybrid Token Masking Reinforcement Learning with Verifiable Rewards for Event Argument Extraction with Multi-Perspective Reasoning

**Authors:** [Jianwen Luo](https://md.research.elamur.ai/free/en/authors/jianwen-luo/), Yongkang Jin, [Yu Hong](https://md.research.elamur.ai/free/en/authors/yu-hong/) and [Jianmin Yao](https://md.research.elamur.ai/free/en/authors/jianmin-yao/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.910/) · [PDF](https://aclanthology.org/2026.acl-long.910.pdf) · [DOI 10.18653/v1/2026.acl-long.910](https://doi.org/10.18653/v1/2026.acl-long.910) · [OpenAlex](https://openalex.org/W7166860196)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Event Argument Extraction (EAE) requires a model to locate the participants of an event in a sentence and label their semantic roles according to a fixed schema. When large language models are trained for EAE with Reinforcement Learning with Verifiable Rewards (RLVR), one scalar reward scores the entire predicted event structure. Gradients, however, are applied to each token separately. As a result, filler and reasoning tokens receive the same credit as the tokens that actually determine roles and spans, which adds noise to training.

The authors propose HTMR, a two-stage post-training recipe:
- **Warm-up:** supervised training on chain-of-thought demonstrations written from five distinct reasoning perspectives.
- **RLVR with DAPO:** policy updates apply only to tokens that fall into at least one of two groups: "forking" tokens with high entropy, or event-critical tokens such as event types, role labels and argument spans. Event-critical tokens often have low entropy, so entropy-only selection tends to miss them.

On ACE05-E, ACE05-E+ and ERE with several LLM backbones, HTMR outperforms both full-token RLVR and entropy-only masking, and it optimizes more stably. It also works as a plug-in for NER and relation classification, which suggests it offers a broader fix for credit assignment in structured prediction.

## Key points
- **Data and setting:** evaluated on the sentence-level benchmarks ACE05-E, ACE05-E+ (both derived from the ACE-2005 corpus) and ERE. Outputs are JSON for deterministic verification. A harder setting without gold triggers or entity mentions is also tested.
- **Warm-up data:** the five perspectives are trigger-centric filtering, role-centric contrastive reasoning, linguistic–heuristic analysis, cognitive-style reasoning and causal–temporal forensics. One perspective is sampled per instance (fixed seed 42). The CoT demonstrations were generated with Qwen3-Max via Alibaba Cloud Model Studio.
- **RL stage and baselines:** the RL stage uses DAPO, a value-free, token-level RLVR optimizer. Baselines are full-token updates and FTMR (Wang et al., 2025), which updates only high-entropy tokens.
- **Cross-task transfer:** on NER (micro P/R/F1) and relation classification (macro P/R/F1 plus Accuracy), HTMR scores best or near-best across both backbones.
- **Code and limitations:** code is released at github.com/York-Gold/HTMR-EAE. The stated limitations are that the study covers only sentence-level EAE and that RLVR costs more compute than SFT because of repeated rollouts.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Soochow University](https://md.research.elamur.ai/free/en/universities/soochow-university/) — University, Suzhou, China · 63 works · 4,507 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works

🧭 Topics (1): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,426 works

## Cite

Cite as: Jianwen Luo, Yongkang Jin, Yu Hong and Jianmin Yao. 2026. HTMR: Hybrid Token Masking Reinforcement Learning with Verifiable Rewards for Event Argument Extraction with Multi-Perspective Reasoning. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{luo2026htmr,
  title = {{HTMR: Hybrid Token Masking Reinforcement Learning with Verifiable Rewards for Event Argument Extraction with Multi-Perspective Reasoning}},
  author = {Jianwen Luo, Yongkang Jin, Yu Hong and Jianmin Yao},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.910},
  url = {https://doi.org/10.18653/v1/2026.acl-long.910}
}
```

- [← previous HSS-Synth: Humanities and Social Sciences Data Synthesis for LLMs](https://md.research.elamur.ai/free/en/papers/peng-2026-hss-synth-humanities-social-sciences/)
- [next → HU at SemEval-2026 Task 6: A Hybrid Discriminative Modeling of Political Clarity and Evasion](https://md.research.elamur.ai/free/en/papers/munawar-2026-hu-semeval-2026-task-6/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/32/)

## References

35 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. OpenAI Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, et al. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/).
2. Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, et al. 2020. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). In Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS ’20, Red Hook, NY, USA. Curran Associates Inc.
3. David G. Clark, L. F. Abbott, and SueYeon Chung. 2021. Credit assignment through broadcasting a global error vector. In Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=David+G%2E+Clark%2C+L%2E+F%2E+Abbott%2C+and+SueYeon+Chung%2E+2021%2E+Credit+assignment+through+broadcasting+a+global+error+vector%2E+In+Neural+Information+Processing+Systems%2E)
4. DeepSeek-AI. 2025. [Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/). Preprint, arXiv:2501.12948.
5. George Doddington, Alexis Mitchell, Mark Przybocki, Lance Ramshaw, Stephanie Strassel, and Ralph Weischedel. 2004. [The automatic content extraction (ACE) program – tasks, data, and evaluation](https://md.research.elamur.ai/free/en/papers/doddington-2004-automatic-content-extraction-ace-program/). In Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC‘04), Lisbo…
6. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, et al. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv preprint arXiv:2407.21783.
7. Yucan Guo, Zixuan Li, Xiaolong Jin, Yantao Liu, Yutao Zeng, Wenxuan Liu, Xiang Li, Pan Yang, Long Bai, Jiafeng Guo, et al. 2024. Retrieval-augmented code generation for universal information extraction. In CCF International Conference on Natural Language Processing and Chinese Computing, pages 30–42… [find](https://scholar.google.com/scholar?q=Yucan+Guo%2C+Zixuan+Li%2C+Xiaolong+Jin%2C+Yantao+Liu%2C+Yutao+Zeng%2C+Wenxuan+Liu%2C+Xiang+Li%2C+Pan+Yang%2C+Long+Bai%2C+Jiafeng+Guo%2C+et+al%2E+2024%2E+Retrieval%2Daugmented+code+generation+for+universal+information+extractio)
8. Ridong Han, Chaohao Yang, Tao Peng, Prayag Tiwari, Xiang Wan, Lu Liu, and Benyou Wang. 2023. An empirical study on information extraction using large language models. arXiv preprint arXiv:2305.14450. — [arXiv:2305.14450](https://arxiv.org/abs/2305.14450) [find](https://scholar.google.com/scholar?q=Ridong+Han%2C+Chaohao+Yang%2C+Tao+Peng%2C+Prayag+Tiwari%2C+Xiang+Wan%2C+Lu+Liu%2C+and+Benyou+Wang%2E+2023%2E+An+empirical+study+on+information+extraction+using+large+language+models%2E+arXiv+preprint+arXiv%3A2305%2E14450%2E+)
9. Iris Hendrickx, Su Nam Kim, Zornitsa Kozareva, Preslav Nakov, Diarmuid Ó Séaghdha, Sebastian Padó, Marco Pennacchiotti, Lorenza Romano, and Stan Szpakowicz. 2010. [SemEval-2010 task 8: Multi-way classification of semantic relations between pairs of nominals](https://md.research.elamur.ai/free/en/papers/hendrickx-2010-semeval-2010-task-8-multi/). In Proceedings of the 5th International Wo…
10. Zijin Hong and Jian Liu. 2024. Towards better question generation in QA-based event extraction. In Findings of the Association for Computational Linguistics: ACL 2024, pages 9025–9038, Bangkok, Thailand. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Zijin+Hong+and+Jian+Liu%2E+2024%2E+Towards+better+question+generation+in+QA%2Dbased+event+extraction%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+ACL+2024%2C+pages+9025%E2%80%939038%2C+Bangkok%2C+Thaila)
11. Solomon Kullback and Richard A Leibler. 1951. On information and sufficiency. The annals of mathematical statistics, 22(1):79–86. [find](https://scholar.google.com/scholar?q=Solomon+Kullback+and+Richard+A+Leibler%2E+1951%2E+On+information+and+sufficiency%2E+The+annals+of+mathematical+statistics%2C+22%281%29%3A79%E2%80%9386%2E)
12. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. 2023. [Efficient memory management for large language model serving with pagedattention](https://md.research.elamur.ai/free/en/papers/kwon-2023-efficient-memory-management-large-language/). In Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles.
13. Zhongqiu Li, Shiquan Wang, Ruiyu Fang, Mengjiao Bao, Zhenhe Wu, Shuangyong Song, Yongxiang Li, and Zhongjiang He. 2025. Mr-uie: multi-perspective reasoning with reinforcement learning for universal information extraction. Vicinagearth, 2. [find](https://scholar.google.com/scholar?q=Zhongqiu+Li%2C+Shiquan+Wang%2C+Ruiyu+Fang%2C+Mengjiao+Bao%2C+Zhenhe+Wu%2C+Shuangyong+Song%2C+Yongxiang+Li%2C+and+Zhongjiang+He%2E+2025%2E+Mr%2Duie%3A+multi%2Dperspective+reasoning+with+reinforcement+learning+for+universal+in)
14. Ying Lin, Heng Ji, Fei Huang, and Lingfei Wu. 2020. [A joint neural model for information extraction with global features](https://md.research.elamur.ai/free/en/papers/lin-2020-joint-neural-model-information-extraction/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7999–8009, Online. Association for Computational Linguistics.
15. Zizheng Lin, Hongming Zhang, and Yangqiu Song. 2023. Global constraints with prompting for zero-shot event argument classification. In Findings of the Association for Computational Linguistics: EACL 2023, pages 2527–2538, Dubrovnik, Croatia. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Zizheng+Lin%2C+Hongming+Zhang%2C+and+Yangqiu+Song%2E+2023%2E+Global+constraints+with+prompting+for+zero%2Dshot+event+argument+classification%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+EACL+2)
16. Jianwen Luo, Yu Hong, Shuai Yang, and Jianmin Yao. 2025. REAR: Reinforced reasoning optimization for event argument extraction with relation-aware support. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 7957–7972, Suzhou, China. Association for Computational Linguist… [find](https://scholar.google.com/scholar?q=Jianwen+Luo%2C+Yu+Hong%2C+Shuai+Yang%2C+and+Jianmin+Yao%2E+2025%2E+REAR%3A+Reinforced+reasoning+optimization+for+event+argument+extraction+with+relation%2Daware+support%2E+In+Findings+of+the+Association+for+Computati)
17. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, et al. 2022. [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/). In Advances in Neural Information Processing Systems, volume 35, pages 27730–27744. Curran Associates, Inc.
18. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347. [find](https://scholar.google.com/scholar?q=John+Schulman%2C+Filip+Wolski%2C+Prafulla+Dhariwal%2C+Alec+Radford%2C+and+Oleg+Klimov%2E+2017%2E+Proximal+policy+optimization+algorithms%2E+arXiv+preprint+arXiv%3A1707%2E06347%2E)
19. Zhiyi Song, Ann Bies, Stephanie Strassel, Tom Riese, Justin Mott, Joe Ellis, Jonathan Wright, Seth Kulick, Neville Ryant, and Xiaoyi Ma. 2015. [From light to rich ERE: Annotation of entities, relations, and events](https://md.research.elamur.ai/free/en/papers/song-2015-light-rich-ere-annotation-entities/). In Proceedings of the 3rd Workshop on EVENTS: Definition, Detection, Coreference, and…
20. Benjamin Strauss, Bethany Toma, Alan Ritter, Marie-Catherine de Marneffe, and Wei Xu. 2016. Results of the WNUT16 named entity recognition shared task. In Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT), pages 138–144, Osaka, Japan. [find](https://scholar.google.com/scholar?q=Benjamin+Strauss%2C+Bethany+Toma%2C+Alan+Ritter%2C+Marie%2DCatherine+de+Marneffe%2C+and+Wei+Xu%2E+2016%2E+Results+of+the+WNUT16+named+entity+recognition+shared+task%2E+In+Proceedings+of+the+2nd+Workshop+on+Noisy+User)
21. The COLING 2016 Organizing Committee. [find](https://scholar.google.com/scholar?q=The+COLING+2016+Organizing+Committee%2E)
22. Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al. 2024. [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://md.research.elamur.ai/free/en/papers/gemini-team-2024-gemini-1-5-unlocking-multimodal/). arXiv preprint arXiv:2403.05530.
23. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. 2023. [Llama 2: Open foundation and fine-tuned chat models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/). arXiv preprint arXiv:2307.09288.
24. Lin, Kai Dang, Keming Lu, Keqin Chen, Kexin Yang, Mei Li, Mingfeng Xue, Na Ni, Pei Zhang, Peng Wang, Ru Peng, Rui Men, Ruize Gao, Runji Lin, Shijie Wang, Shuai Bai, Sinan Tan, Tianhang Zhu, Tianhao Li, Tianyu Liu, Wenbin Ge, Xiaodong Deng, Xiaohuan Zhou, Xingzhang Ren, Xinyu Zhang, Xipin Wei, Xuanch… [find](https://scholar.google.com/scholar?q=Lin%2C+Kai+Dang%2C+Keming+Lu%2C+Keqin+Chen%2C+Kexin+Yang%2C+Mei+Li%2C+Mingfeng+Xue%2C+Na+Ni%2C+Pei+Zhang%2C+Peng+Wang%2C+Ru+Peng%2C+Rui+Men%2C+Ruize+Gao%2C+Runji+Lin%2C+Shijie+Wang%2C+Shuai+Bai%2C+Sinan+Tan%2C+Tianhang+Zhu%2C+Tianhao+Li)
25. Ben Wang. 2021. Mesh-Transformer-JAX: Model-Parallel Implementation of Transformer Language Model with JAX. [https://github.com/](https://github.com/) kingoflolz/mesh-transformer-jax. [↗](https://github.com/)
26. Shenzhi Wang, Le Yu, Chang Gao, Chujie Zheng, Shixuan Liu, Rui Lu, Kai Dang, Xiong-Hui Chen, Jianxin Yang, Zhenru Zhang, Yuqiong Liu, An Yang, Andrew Zhao, Yang Yue, Shiji Song, Bowen Yu, Gao Huang, and Junyang Lin. 2025. [Beyond the 80/20 rule: High-entropy minority tokens drive effective reinforcem…](https://md.research.elamur.ai/free/en/papers/wang-2025-80-20-rule-high-entropy/)
27. Sijia Wang and Lifu Huang. 2024. Debate as optimization: Adaptive conformal prediction and diverse retrieval for event extraction. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 16422–16435, Miami, Florida, USA. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Sijia+Wang+and+Lifu+Huang%2E+2024%2E+Debate+as+optimization%3A+Adaptive+conformal+prediction+and+diverse+retrieval+for+event+extraction%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+EMNLP+2)
28. Xingyao Wang, Sha Li, and Heng Ji. 2023. [Code4Struct: Code generation for few-shot event structure prediction](https://md.research.elamur.ai/free/en/papers/wang-2023-code4struct-code-generation-few-shot/). In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3640–3663, Toronto, Canada. Association for Computational Linguisti…
29. Yunhao Wei, Kai Shuang, Zhiyi Li, and Chenrui Mao. 2025. How do LLMs’ preferences affect event argument extraction? CAT: Addressing preference traps in unsupervised EAE. In Findings of the Association for Computational Linguistics: ACL 2025, pages 19529–19543, Vienna, Austria. Association for Comput… [find](https://scholar.google.com/scholar?q=Yunhao+Wei%2C+Kai+Shuang%2C+Zhiyi+Li%2C+and+Chenrui+Mao%2E+2025%2E+How+do+LLMs%E2%80%99+preferences+affect+event+argument+extraction%3F+CAT%3A+Addressing+preference+traps+in+unsupervised+EAE%2E+In+Findings+of+the+Association)
30. 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, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jing Zhou, Jin… — [Qwen3 Technical Report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/)
31. 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, Junyang Lin, Kai Dang, Keming Lu, Keqin Bao, Kexin Yang, Le Yu, Mei Li, Mingfeng Xue, Pei… [find](https://scholar.google.com/scholar?q=An+Yang%2C+Baosong+Yang%2C+Beichen+Zhang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+Haoran+Wei%2C+Huan+Lin%2C+Jian+Yang%2C+Jianhong+Tu%2C+Jianwei+Zhang%2C+Jianxin+Yang%2C+Jiaxi+Yang%2C+Jin)
32. Yu Yang, Jinyu Guo, Kai Shuang, and Chenrui Mao. 2024c. Scented-EAE: Stage-customized entity type embedding for event argument extraction. In Findings of the Association for Computational Linguistics: ACL 2024, pages 5222–5235, Bangkok, Thailand. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Yu+Yang%2C+Jinyu+Guo%2C+Kai+Shuang%2C+and+Chenrui+Mao%2E+2024c%2E+Scented%2DEAE%3A+Stage%2Dcustomized+entity+type+embedding+for+event+argument+extraction%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A)
33. Qiying Yu, Zheng Zhang, Ruofei Zhu, Yufeng Yuan, Xiaochen Zuo, Yu Yue, Weinan Dai, Tiantian Fan, Gaohong Liu, Lingjun Liu, et al. 2025. [Dapo: An open-source llm reinforcement learning system at scale](https://md.research.elamur.ai/free/en/papers/yu-2025-dapo-open-source-llm-reinforcement/). arXiv preprint arXiv:2503.14476.
34. Qihao Zhu Runxin Xu Junxiao Song Mingchuan Zhang Y.K. Li Y. Wu Daya Guo Zhihong Shao, Peiyi Wang. 2024. [Deepseekmath: Pushing the limits of mathematical reasoning in open language models](https://md.research.elamur.ai/free/en/papers/shao-2024-deepseekmath-pushing-limits-mathematical-reasoning/).
35. An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, Guanting Dong, Haoran Wei, Huan Lin, Jialong Tang, Jialin Wang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Ma, Jin Xu, Jingren Zhou, Jinze Bai, Jinzheng He, Junyang [find](https://scholar.google.com/scholar?q=An+Yang%2C+Baosong+Yang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chang+Zhou%2C+Chengpeng+Li%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+Guanting+Dong%2C+Haoran+Wei%2C+Huan+Lin%2C+Jialong+Tang%2C+Jialin+Wang%2C+Jian+Yang%2C+Jian)

*Updated 1 November 2026*