---
title: "Boundary-Aware LLM Augmentation for Low-Resource Event"
description: "The study offers practical guidance for building EAE systems in specialised, low-resource domains such as healthcare. 31 references."
authors: ["Zhaoyue Sun", "Gabriele Pergola", "Yulan He"]
year: 2026
venue: "Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.eacl-long.230/"
doi: "10.18653/v1/2026.eacl-long.230"
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/sun-2026-boundary-aware-llm-augmentation-low/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/sun-2026-boundary-aware-llm-augmentation-low/)

[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/10/) / Boundary-Aware LLM Augmentation for Low-Resource Event Argument Extraction

# Boundary-Aware LLM Augmentation for Low-Resource Event Argument Extraction

**Authors:** Zhaoyue Sun, Gabriele Pergola and [Yulan He](https://md.research.elamur.ai/free/en/authors/yulan-he/) · **Year:** 2026 · **Venue:** [Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/eacl/) ([EACL 2026](https://md.research.elamur.ai/free/en/venues/eacl/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.eacl-long.230/) · [PDF](https://aclanthology.org/2026.eacl-long.230.pdf) · [DOI 10.18653/v1/2026.eacl-long.230](https://doi.org/10.18653/v1/2026.eacl-long.230) · [OpenAlex](https://openalex.org/W7140081224)

**Citations:** 1 citations (OpenAlex, 2026-10-14)

## Summary
Event argument extraction (EAE) finds the participants of an event and assigns each one a role. It depends on expensive annotation, so models struggle when labelled data are scarce. The authors study how large language models can produce extra EAE training data without damaging argument spans, a property they call boundary sensitivity. They compare four LLM-driven strategies:
- replacing argument spans with new, role-consistent ones;
- rewriting only the non-argument context (adjunctions);
- applying both changes together;
- having the LLM annotate new text itself.

GPT-4o-Mini and DeepSeek-R1-7B serve as generators. The downstream extractor is a QA-style generative model on a Flan-T5 backbone (Flan-T5 EEQA), tested on four general and domain-specific benchmarks. Methods that keep argument positions fixed outperform annotation generation on both Micro_F1 and Macro_F1. They mainly reduce spurious and partially matched spans, which helps both frequent and rare roles. The study offers practical guidance for building EAE systems in specialised, low-resource domains such as healthcare.

## Key points
- Benchmarks: ACE, GENEVA, PHEE and CASIE. The extraction model is Flan-T5 EEQA, and the data generators are GPT-4o-Mini and DeepSeek-R1-7B.
- The best boundary-aware method depends on the dataset:
  - Argument replacement works best where roles are clearly defined and domain-specific.
  - Adjunction rewriting suits datasets with vaguer roles, such as ACE, or weaker generator models.
- Compared with a non-LLM boundary-aware baseline (Mask-then-Fill), LLMs gain the most from the argument replacement strategy.
- After filtering, GPT-4o-Mini keeps far more of its generated samples than DeepSeek-R1-7B. ACE has the highest retention rate. DeepSeek-R1-7B tends to hallucinate, alter non-argument text, make spelling errors and mix in other languages.
- Higher augmentation ratios give steadier improvements, but the gains plateau because synthetic samples are homogeneous. Augmented data still helps as the original training set grows.

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

📚 Shelves (4): [🖥️ 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

🧭 Topics (2): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works · [🌱 Low-resource languages](https://md.research.elamur.ai/free/en/topics/low-resource-languages/) · 267 works

## Cite

Cite as: Zhaoyue Sun, Gabriele Pergola and Yulan He. 2026. Boundary-Aware LLM Augmentation for Low-Resource Event Argument Extraction. Proceedings of the 19th Conference of the European Chapter 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{sun2026boundary,
  title = {{Boundary-Aware LLM Augmentation for Low-Resource Event Argument Extraction}},
  author = {Zhaoyue Sun, Gabriele Pergola and Yulan He},
  booktitle = {Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.eacl-long.230},
  url = {https://doi.org/10.18653/v1/2026.eacl-long.230}
}
```

- [← previous BoostedCats at BEA 2026 Shared Task 1: What Makes a Word Hard to Learn? Modeling L1 Influence on English Vocabulary Difficulty](https://md.research.elamur.ai/free/en/papers/martins-2026-boostedcats-bea-2026-shared-task/)
- [next → Breaking the Evaluation Paradox: Evaluating High-Entropy Search with Computationally Irreducible Constraints](https://md.research.elamur.ai/free/en/papers/wu-2026-breaking-evaluation-paradox-evaluating-high/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/10/)

## References

31 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Yunxuan Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, et al. 2024. Scaling instruction-finetuned language models. Journal of Machine Learning Research, 25(70):1–53. [find](https://scholar.google.com/scholar?q=Hyung+Won+Chung%2C+Le+Hou%2C+Shayne+Longpre%2C+Barret+Zoph%2C+Yi+Tay%2C+William+Fedus%2C+Yunxuan+Li%2C+Xuezhi+Wang%2C+Mostafa+Dehghani%2C+Siddhartha+Brahma%2C+et+al%2E+2024%2E+Scaling+instruction%2Dfinetuned+language+models%2E+J)
2. 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…
3. Xinya Du and Claire Cardie. 2020. [Event extraction by answering (almost) natural questions](https://md.research.elamur.ai/free/en/papers/du-2020-event-extraction-answering-almost-natural/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 671–683, Online. Association for Computational Linguistics.
4. Jun Gao, Changlong Yu, Wei Wang, Huan Zhao, and Ruifeng Xu. 2022. Mask-then-fill: A flexible and effective data augmentation framework for event extraction. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 4537–4544, Abu Dhabi, United Arab Emirates. Association for Com… [find](https://scholar.google.com/scholar?q=Jun+Gao%2C+Changlong+Yu%2C+Wei+Wang%2C+Huan+Zhao%2C+and+Ruifeng+Xu%2E+2022%2E+Mask%2Dthen%2Dfill%3A+A+flexible+and+effective+data+augmentation+framework+for+event+extraction%2E+In+Findings+of+the+Association+for+Computat)
5. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al. 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/). arXiv preprint arXiv:2501.12948.
6. Shiming He, Yu Hong, Shuai Yang, Jianmin Yao, and Guodong Zhou. 2024. Demonstration retrieval-augmented generative event argument extraction. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 4617–4625,… [find](https://scholar.google.com/scholar?q=Shiming+He%2C+Yu+Hong%2C+Shuai+Yang%2C+Jianmin+Yao%2C+and+Guodong+Zhou%2E+2024%2E+Demonstration+retrieval%2Daugmented+generative+event+argument+extraction%2E+In+Proceedings+of+the+2024+Joint+International+Conference+)
7. Yuxin He, Jingyue Hu, and Buzhou Tang. 2023. Revisiting event argument extraction: Can EAE models learn better when being aware of event co-occurrences? In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12542– 12556, Toronto, Ca… [find](https://scholar.google.com/scholar?q=Yuxin+He%2C+Jingyue+Hu%2C+and+Buzhou+Tang%2E+2023%2E+Revisiting+event+argument+extraction%3A+Can+EAE+models+learn+better+when+being+aware+of+event+co%2Doccurrences%3F+In+Proceedings+of+the+61st+Annual+Meeting+of+th)
8. Ruixin Hong, Hongming Zhang, Xintong Yu, and Changshui Zhang. 2022. Learning event extraction from a few guideline examples. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 30:2955–2967. [find](https://scholar.google.com/scholar?q=Ruixin+Hong%2C+Hongming+Zhang%2C+Xintong+Yu%2C+and+Changshui+Zhang%2E+2022%2E+Learning+event+extraction+from+a+few+guideline+examples%2E+IEEE%2FACM+Transactions+on+Audio%2C+Speech%2C+and+Language+Processing%2C+30%3A2955%E2%80%9329)
9. I-Hung Hsu, Kuan-Hao Huang, Elizabeth Boschee, Scott Miller, Prem Natarajan, Kai-Wei Chang, and Nanyun Peng. 2022. [DEGREE: A data-efficient generation-based event extraction model](https://md.research.elamur.ai/free/en/papers/hsu-2022-degree-data-efficient-generation-based/). In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: H…
10. Jonas Hübotter, Sascha Bongni, Ido Hakimi, and Andreas Krause. 2025. Efficiently learning at test-time: Active fine-tuning of llms. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Jonas+H%C3%BCbotter%2C+Sascha+Bongni%2C+Ido+Hakimi%2C+and+Andreas+Krause%2E+2025%2E+Efficiently+learning+at+test%2Dtime%3A+Active+fine%2Dtuning+of+llms%2E+In+The+Thirteenth+International+Conference+on+Learning+Representatio)
11. Fayuan Li, Weihua Peng, Yuguang Chen, Quan Wang, Lu Pan, Yajuan Lyu, and Yong Zhu. 2020. [Event extraction as multi-turn question answering](https://md.research.elamur.ai/free/en/papers/li-2020-event-extraction-as-multi-turn/). In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 829–838, Online. Association for Computational Linguistics.
12. Yaojie Lu, Hongyu Lin, Jin Xu, Xianpei Han, Jialong Tang, Annan Li, Le Sun, Meng Liao, and Shaoyi Chen. 2021. [Text2Event: Controllable sequence-to-structure generation for end-to-end event extraction](https://md.research.elamur.ai/free/en/papers/lu-2021-text2event-controllable-sequence-structure-generation/). In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the…
13. Yaojie Lu, Qing Liu, Dai Dai, Xinyan Xiao, Hongyu Lin, Xianpei Han, Le Sun, and Hua Wu. 2022. Unified structure generation for universal information extraction. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5755–5772, Dublin… [find](https://scholar.google.com/scholar?q=Yaojie+Lu%2C+Qing+Liu%2C+Dai+Dai%2C+Xinyan+Xiao%2C+Hongyu+Lin%2C+Xianpei+Han%2C+Le+Sun%2C+and+Hua+Wu%2E+2022%2E+Unified+structure+generation+for+universal+information+extraction%2E+In+Proceedings+of+the+60th+Annual+Meeti)
14. Manfu Ma, Xiaoxue Li, Yong Li, Xinyu Zhao, Xia Wang, and Hai Jia. 2022a. Small sample medical event extraction based on data augmentation. In International Conference on Biomedical and Intelligent Systems (IC-BIS 2022), volume 12458, pages 823– 833. SPIE. [find](https://scholar.google.com/scholar?q=Manfu+Ma%2C+Xiaoxue+Li%2C+Yong+Li%2C+Xinyu+Zhao%2C+Xia+Wang%2C+and+Hai+Jia%2E+2022a%2E+Small+sample+medical+event+extraction+based+on+data+augmentation%2E+In+International+Conference+on+Biomedical+and+Intelligent+Sys)
15. Yubo Ma, Yixin Cao, Yong Hong, and Aixin Sun. 2023. [Large language model is not a good few-shot information extractor, but a good reranker for hard samples!](https://md.research.elamur.ai/free/en/papers/ma-2023-large-language-model-is-not/) In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 10572–10601, Singapore. Association for Computational Linguisti…
16. Yubo Ma, Zehao Wang, Yixin Cao, Mukai Li, Meiqi Chen, Kun Wang, and Jing Shao. 2022b. [Prompt for extraction? PAIE: Prompting argument interaction for event argument extraction](https://md.research.elamur.ai/free/en/papers/ma-2022-prompt-extraction-paie-prompting-argument/). In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6…
17. Zihao Meng, Tao Liu, Heng Zhang, Kai Feng, and Peng Zhao. 2024. CEAN: Contrastive event aggregation network with LLM-based augmentation for event extraction. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages… [find](https://scholar.google.com/scholar?q=Zihao+Meng%2C+Tao+Liu%2C+Heng+Zhang%2C+Kai+Feng%2C+and+Peng+Zhao%2E+2024%2E+CEAN%3A+Contrastive+event+aggregation+network+with+LLM%2Dbased+augmentation+for+event+extraction%2E+In+Proceedings+of+the+18th+Conference+of+t)
18. OpenAI. 2024. Gpt-4o mini: Advancing cost-efficient intelligence. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2024%2E+Gpt%2D4o+mini%3A+Advancing+cost%2Defficient+intelligence%2E)
19. Giovanni Paolini, Ben Athiwaratkun, Jason Krone, Ma Jie, Alessandro Achille, Rishita Anubhai, Cicero Nogueira dos Santos, Bing Xiang, Stefano Soatto, et al. 2021. Structured prediction as translation between augmented natural languages. In ICLR 2021-9th International Conference on Learning Represent… [find](https://scholar.google.com/scholar?q=Giovanni+Paolini%2C+Ben+Athiwaratkun%2C+Jason+Krone%2C+Ma+Jie%2C+Alessandro+Achille%2C+Rishita+Anubhai%2C+Cicero+Nogueira+dos+Santos%2C+Bing+Xiang%2C+Stefano+Soatto%2C+et+al%2E+2021%2E+Structured+prediction+as+translation+)
20. Tanmay Parekh, I-Hung Hsu, Kuan-Hao Huang, Kai-Wei Chang, and Nanyun Peng. 2023. GENEVA: Benchmarking generalizability for event argument extraction with hundreds of event types and argument roles. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1:… [find](https://scholar.google.com/scholar?q=Tanmay+Parekh%2C+I%2DHung+Hsu%2C+Kuan%2DHao+Huang%2C+Kai%2DWei+Chang%2C+and+Nanyun+Peng%2E+2023%2E+GENEVA%3A+Benchmarking+generalizability+for+event+argument+extraction+with+hundreds+of+event+types+and+argument+roles%2E+In)
21. Amir Pouran Ben Veyseh, Tuan Ngo Nguyen, and Thien Huu Nguyen. 2020. Graph transformer networks with syntactic and semantic structures for event argument extraction. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3651–3661, Online. Association for Computational Lingu… [find](https://scholar.google.com/scholar?q=Amir+Pouran+Ben+Veyseh%2C+Tuan+Ngo+Nguyen%2C+and+Thien+Huu+Nguyen%2E+2020%2E+Graph+transformer+networks+with+syntactic+and+semantic+structures+for+event+argument+extraction%2E+In+Findings+of+the+Association+for)
22. Sijia Wang and Lifu Huang. 2024. Targeted augmentation for low-resource event extraction. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 4414–4428, Mexico City, Mexico. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Sijia+Wang+and+Lifu+Huang%2E+2024%2E+Targeted+augmentation+for+low%2Dresource+event+extraction%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+NAACL+2024%2C+pages+4414%E2%80%934428%2C+Mexico+City%2C+Mexico)
23. Jason Wei and Kai Zou. 2019. [EDA: Easy data augmentation techniques for boosting performance on text classification tasks](https://md.research.elamur.ai/free/en/papers/wei-2019-eda-easy-data-augmentation-techniques/). In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP…
24. Wentao Wu, Hongsong Li, Haixun Wang, and Kenny Q Zhu. 2012. Probase: A probabilistic taxonomy for text understanding. In Proceedings of the 2012 ACM SIGMOD international conference on management of data, pages 481–492. [find](https://scholar.google.com/scholar?q=Wentao+Wu%2C+Hongsong+Li%2C+Haixun+Wang%2C+and+Kenny+Q+Zhu%2E+2012%2E+Probase%3A+A+probabilistic+taxonomy+for+text+understanding%2E+In+Proceedings+of+the+2012+ACM+SIGMOD+international+conference+on+management+of+da)
25. Sen Yang, Dawei Feng, Linbo Qiao, Zhigang Kan, and Dongsheng Li. 2019. [Exploring pre-trained language models for event extraction and generation](https://md.research.elamur.ai/free/en/papers/yang-2019-exploring-pre-trained-language-models/). In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5284– 5294, Florence, Italy. Association for Computation…
26. Oscar Sainz, Iker García-Ferrero, Rodrigo Agerri, Oier Lopez de Lacalle, German Rigau, and Eneko Agirre. 2024. [Gollie: Annotation guidelines improve zero-shot information-extraction](https://md.research.elamur.ai/free/en/papers/sainz-2023-gollie-annotation-guidelines-improve-zero/). In The Twelfth International Conference on Learning Representations.
27. Taneeya Satyapanich, Francis Ferraro, and Tim Finin. 2020. Casie: Extracting cybersecurity event information from text. In Proceedings of the AAAI conference on artificial intelligence, volume 34, pages 8749–8757. [find](https://scholar.google.com/scholar?q=Taneeya+Satyapanich%2C+Francis+Ferraro%2C+and+Tim+Finin%2E+2020%2E+Casie%3A+Extracting+cybersecurity+event+information+from+text%2E+In+Proceedings+of+the+AAAI+conference+on+artificial+intelligence%2C+volume+34%2C+pag)
28. Sam Shleifer. 2019. Low resource text classification with ulmfit and backtranslation. arXiv preprint arXiv:1903.09244. — [arXiv:1903.09244](https://arxiv.org/abs/1903.09244) [find](https://scholar.google.com/scholar?q=Sam+Shleifer%2E+2019%2E+Low+resource+text+classification+with+ulmfit+and+backtranslation%2E+arXiv+preprint+arXiv%3A1903%2E09244%2E+%E2%80%94+%5BarXiv%3A1903%2E09244%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1903%2E09244%29)
29. Zhaoyue Sun, Jiazheng Li, Gabriele Pergola, Byron Wallace, Bino John, Nigel Greene, Joseph Kim, and Yulan He. 2022. PHEE: A dataset for pharmacovigilance event extraction from text. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 5571–5587, Abu Dhabi,… [find](https://scholar.google.com/scholar?q=Zhaoyue+Sun%2C+Jiazheng+Li%2C+Gabriele+Pergola%2C+Byron+Wallace%2C+Bino+John%2C+Nigel+Greene%2C+Joseph+Kim%2C+and+Yulan+He%2E+2022%2E+PHEE%3A+A+dataset+for+pharmacovigilance+event+extraction+from+text%2E+In+Proceedings+of+)
30. Zhaoyue Sun, Gabriele Pergola, Byron Wallace, and Yulan He. 2024. Leveraging ChatGPT in pharmacovigilance event extraction: An empirical study. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers), pages 344–357, St.… [find](https://scholar.google.com/scholar?q=Zhaoyue+Sun%2C+Gabriele+Pergola%2C+Byron+Wallace%2C+and+Yulan+He%2E+2024%2E+Leveraging+ChatGPT+in+pharmacovigilance+event+extraction%3A+An+empirical+study%2E+In+Proceedings+of+the+18th+Conference+of+the+European+Ch)
31. Andrew Trotman, Antti Puurula, and Blake Burgess. 2014. Improvements to bm25 and language models examined. In Proceedings of the 2014 Australasian Document Computing Symposium, pages 58–65. [find](https://scholar.google.com/scholar?q=Andrew+Trotman%2C+Antti+Puurula%2C+and+Blake+Burgess%2E+2014%2E+Improvements+to+bm25+and+language+models+examined%2E+In+Proceedings+of+the+2014+Australasian+Document+Computing+Symposium%2C+pages+58%E2%80%9365%2E)

*Updated 31 October 2026*