Elamur Research⌕
☰
home / papers / 2026 / Zero-Shot Open-Schema Entity Structure Discovery

Zero-Shot Open-Schema Entity Structure Discovery

Paper · 2026 · Xueqiang Xu, Jinfeng Xiao, James Barry et al.

Summary

Most LLM-based methods for extracting entities and their attribute–value descriptions depend on a fixed schema or labeled examples, so they miss attributes nobody anticipated. The authors define a schema-free version of the task, Open-Schema Entity Structure Discovery (OpenESD). Given a document and the entity types a user cares about, a system must find the relevant entities and build a set of ⟨attribute, value⟩ pairs for each one.

Their method, ZOES, needs no training and no annotation. It works in three steps:

  1. It takes the LLM's own zero-shot triplets and enriches them by rereading the text, guided by values and broad root attributes.
  2. It uses the dependencies among entity, attribute and value to find vague or overly coarse triplets and repair them.
  3. It merges the cleaned triplets into one structure per entity.

The authors tested ZOES with several backbone models on a new dataset covering battery science, economics and politics. It outperformed CoT and Few-Shot prompting in every domain, with a reported absolute F1 gain of 10.64%. The results suggest that organizing the extraction process works better than prompting alone for building knowledge graphs.

Key points

  • Task and data: The paper introduces the OpenESD task, in which no attribute names are predefined. The evaluation set has human-annotated reference triplets in three domains: Battery Science (treated as long-tail), Economics and Politics.
  • Pipeline: ZOES combines three stages: value-anchored enrichment, triplet granularity refinement based on mutual dependencies, and unification into entity structures.
  • Results: ZOES achieved a +10.64% absolute F1 improvement and consistently beat CoT and Few-Shot baselines across backbones. Per-document win rates show that the gains are not driven by a handful of information-dense texts.
  • Error analysis: Precision drops in some cases for two reasons. Broad root attributes sometimes yield loose, sentence-like outputs. Implicit attributes can produce vague names such as "features" or "includes".
  • Limitations: The multi-round pipeline raises inference cost. Evaluation depends on manual annotation and a weighted scoring function, which may be subjective and hard to scale.

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

🎓University of Illinois Urbana-ChampaignUrbana · United States209 works · 71,394 citations🏢IBMArmonk · United States154 works · 72,606 citations🏢AmazonSeattle · United States128 works · 41,700 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 works

Cite

Cite as Xueqiang Xu, Jinfeng Xiao, James Barry, Mohab Elkaref, Jiaru Zou, Pengcheng Jiang, Yunyi Zhang, Maxwell J Giammona, Geeth De Mel and Jiawei Han. 2026. Zero-Shot Open-Schema Entity Structure Discovery. 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. DOI 10.18653/v1/2026.eacl-long.354

@inproceedings{xu2026zero,
  title = {{Zero-Shot Open-Schema Entity Structure Discovery}},
  author = {Xueqiang Xu, Jinfeng Xiao, James Barry, Mohab Elkaref, Jiaru Zou, Pengcheng Jiang, Yunyi Zhang, Maxwell J Giammona, Geeth {De Mel} and Jiawei Han},
  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.354},
  url = {https://doi.org/10.18653/v1/2026.eacl-long.354}
}

References

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

  1. Vahan Arsenyan, Spartak Bughdaryan, Fadi Shaya, Kent Wilson Small, and Davit Shahnazaryan. 2024. Large language models for biomedical knowledge graph construction: Information extraction from EMR notes. In Proceedings of the 23rd Workshop on Biomedical Natural Language Processing, pages 295–317, Ban… find
  2. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901.
  3. Chih-Yao Chen and Cheng-Te Li. 2021. ZS-BERT: Towards zero-shot relation extraction with attribute representation learning. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3470–3479, Online. Asso…
  4. John Dagdelen, Alexander Dunn, Sanghoon Lee, Nicholas Walker, Andrew S. Rosen, Gerbrand Ceder, Kristin A. Persson, and Anubhav Jain. 2024. Structured information extraction from scientific text with large language models. Nature Communications, 15(1):1418.
  5. Kuicai Dong, Zhao Yilin, Aixin Sun, Jung-Jae Kim, and Xiaoli Li. 2021. DocOIE: A document-level context-aware dataset for OpenIE. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 2377–2389, Online. Association for Computational Linguistics. find
  6. Alexander Dunn, John Dagdelen, Nicholas Walker, Sanghoon Lee, Andrew S. Rosen, Gerbrand Ceder, Kristin Persson, and Anubhav Jain. 2022. Structured information extraction from complex scientific text with fine-tuned large language models. Preprint, arXiv:2212.05238. — [arXiv:2212.05238](https://arxiv.org/abs/2212.05238) find
  7. Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, Dasha Metropolitansky, Robert Osazuwa Ness, and Jonathan Larson. 2025. From local to global: A graph rag approach to query-focused summarization. Preprint, arXiv:2404.16130. find
  8. IBM Granite Team. 2024. Granite 3.0 language models. find
  9. Bernal Jiménez Gutiérrez, Yiheng Shu, Weijian Qi, Sizhe Zhou, and Yu Su. 2025. From rag to memory: Non-parametric continual learning for large language models. Preprint, arXiv:2502.14802.
  10. Pengcheng Jiang, Lang Cao, Ruike Zhu, Minhao Jiang, Yunyi Zhang, Jimeng Sun, and Jiawei Han. 2025. Ras: Retrieval-and-structuring for knowledge-intensive llm generation. arXiv preprint arXiv: 2502.10996. — [arXiv:2502.10996](https://arxiv.org/abs/2502.10996) find
  11. Pengcheng Jiang, Jiacheng Lin, Zifeng Wang, Jimeng Sun, and Jiawei Han. 2024. GenRES: Rethinking evaluation for generative relation extraction in the era of large language models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Hu… find
  12. Yizhu Jiao, Sha Li, Yiqing Xie, Ming Zhong, Heng Ji, and Jiawei Han. 2022. Open-vocabulary argument role prediction for event extraction. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 5404–5418, Abu Dhabi, United Arab Emirates. Association for Computational Linguist… find
  13. Luciano Del Corro and Rainer Gemulla. 2013. Clausie: clause-based open information extraction. In Proceedings of the 22nd International Conference on World Wide Web, WWW ’13, page 355–366, New York, NY, USA. Association for Computing Machinery. find
  14. Yizhu Jiao, Ming Zhong, Sha Li, Ruining Zhao, Siru Ouyang, Heng Ji, and Jiawei Han. 2023. Instruct and extract: Instruction tuning for on-demand information extraction. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 10030–10051, Singapore. Associatio… find
  15. Linyi Ding, Jinfeng Xiao, Sizhe Zhou, Chaoqi Yang, and Jiawei Han. 2024. Topic-oriented open relation extraction with a priori seed generation. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 13834–13845, Miami, Florida, USA. Association for Computati… find
  16. SeongKu Kang, Yunyi Zhang, Pengcheng Jiang, Dongha Lee, Jiawei Han, and Hwanjo Yu. 2024. Taxonomy-guided semantic indexing for academic paper search. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 7169–7184, Miami, Florida, USA. Association for Compu… find
  17. Imed Keraghel, Stanislas Morbieu, and Mohamed Nadif. 2024. A survey on recent advances in named entity recognition. arXiv preprint arXiv:2401.10825. — [arXiv:2401.10825](https://arxiv.org/abs/2401.10825) find
  18. Keshav Kolluru, Muqeeth Mohammed, Shubham Mittal, Soumen Chakrabarti, and Mausam. 2022. Alignment-augmented consistent translation for multilingual open information extraction. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2… find
  19. Omer Levy, Minjoon Seo, Eunsol Choi, and Luke Zettlemoyer. 2017. Zero-shot relation extraction via reading comprehension. In Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), pages 333–342, Vancouver, Canada. Association for Computational Linguistics.
  20. Guozheng Li, Peng Wang, and Wenjun Ke. 2023. Revisiting large language models as zero-shot relation extractors. arXiv preprint arXiv:2310.05028. find
  21. Jing Li, Aixin Sun, Jianglei Han, and Chenliang Li. 2020. A survey on deep learning for named entity recognition. IEEE transactions on knowledge and data engineering, 34(1):50–70. find
  22. Sha Li, Heng Ji, and Jiawei Han. 2021. Document-level event argument extraction by conditional generation. arXiv preprint arXiv:2104.05919.
  23. Zehan Li, Fu Zhang, Wenqing Zhang, Jiawei Li, Zhou Li, Jingwei Cheng, and Tianyue Peng. 2025. Frame first, then extract: A frame-semantic reasoning pipeline for zero-shot relation triplet extraction. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 273… find
  24. Keming Lu, Xiaoman Pan, Kaiqiang Song, Hongming Zhang, Dong Yu, and Jianshu Chen. 2023. PIVOINE: Instruction tuning for open-world entity profiling. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 15108–15127, Singapore. Association for Computational Linguistics. find
  25. Mausam Mausam. 2016. Open information extraction systems and downstream applications. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI’16, page 4074–4077. AAAI Press. find
  26. Zara Nasar, Syed Waqar Jaffry, and Muhammad Kamran Malik. 2021. Named entity recognition and relation extraction: State-of-the-art. ACM Computing Surveys (CSUR), 54(1):1–39. find
  27. Yasumasa Onoe and Greg Durrett. 2020. Fine-grained entity typing for domain independent entity linking. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05):8576–8583. find
  28. OpenAI, Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, et al. 2024. Gpt-4 technical report. Preprint, arXiv:2303.08774.
  29. Liu Pai, Wenyang Gao, Wenjie Dong, Lin Ai, Ziwei Gong, Songfang Huang, Li Zongsheng, Ehsan Hoque, Julia Hirschberg, and Yue Zhang. 2024. A survey on open information extraction from rule-based model to large language model. In Findings of the Association for Computational Linguistics: EMNLP 2024, pa… find
  30. Kevin Pei, Ishan Jindal, and Kevin Chang. 2023. Abstractive open information extraction. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 6146–6158, Singapore. Association for Computational Linguistics. find
  31. Yunjia Qi, Hao Peng, Xiaozhi Wang, Bin Xu, Lei Hou, and Juanzi Li. 2024. ADELIE: Aligning large language models on information extraction. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 7371–7387, Miami, Florida, USA. Association for Computational Li… find
  32. Youngbin Ro, Yukyung Lee, and Pilsung Kang. 2020. Multi^2OIE: Multilingual open information extraction based on multi-head attention with BERT. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 1107–1117, Online. Association for Computational Linguistics. find
  33. Zeliang Tong, Zhuojun Ding, and Wei Wei. 2025. Evo-Prompt: Evolving prompts for enhanced zero-shot named entity recognition with large language models. In Proceedings of the 31st International Conference on Computational Linguistics, pages 5136– 5153, Abu Dhabi, UAE. Association for Computational Li… find
  34. Van-Hien Tran, Hiroki Ouchi, Taro Watanabe, and Yuji Matsumoto. 2022. Improving discriminative learning for zero-shot relation extraction. Proceedings of the 1st Workshop on Semiparametric Methods in NLP: Decoupling Logic from Knowledge. find
  35. Michael Vasilkovsky, Anton Alekseev, Valentin Malykh, Ilya Shenbin, Elena Tutubalina, Dmitriy Sa-likhov, Mikhail Stepnov, Andrei Chertok, and Sergey Nikolenko. 2022. DetIE: Multilingual Open Information Extraction Inspired by Object Detection. In Proceedings of the 36th AAAI Conference on Artificial… find
  36. Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. 2022. Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533.
  37. Joe H Ward Jr. 1963. Hierarchical grouping to optimize an objective function. Journal of the American statistical association, 58(301):236–244. find
  38. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35:24824–24837.
  39. Xiang Wei, Xingyu Cui, Ning Cheng, Xiaobin Wang, Xin Zhang, Shen Huang, Pengjun Xie, Jinan Xu, Yufeng Chen, Meishan Zhang, Yong Jiang, and Wenjuan Han. 2023. Zero-shot information extraction via chatting with chatgpt. ArXiv, abs/2302.10205.
  40. Haolun Wu, Ye Yuan, Liana Mikaelyan, Alexander Meulemans, Xue Liu, James Hensman, and Bhaskar Mitra. 2024. Learning to extract structured entities using language models. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 6817–6834, Miami, Florida, USA. A… find
  41. Lilong Xue, Dan Zhang, Yuxiao Dong, and Jie Tang. 2024. Autore: Document-level relation extraction with large language models. arXiv preprint arXiv:2403.14888.
  42. Li Yang, Qifan Wang, Zac Yu, Anand Kulkarni, Sumit Sanghai, Bin Shu, Jon Elsas, and Bhargav Kanagal. 2022. Mave: A product dataset for multi-source attribute value extraction. WSDM ’22, page 1256–1265, New York, NY, USA. Association for Computing Machinery. find
  43. Bowen Yu, Yucheng Wang, Tingwen Liu, Hongsong Zhu, Limin Sun, and Bin Wang. 2021. Maximal clique based non-autoregressive open information extraction. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9696–9706, Online and Punta Cana, Dominican Republic… find
  44. Lingfeng Zhong, Jia Wu, Qian Li, Hao Peng, and Xindong Wu. 2023a. A comprehensive survey on automatic knowledge graph construction. ACM Comput. Surv., 56(4). find
  45. Ming Zhong, Siru Ouyang, Minhao Jiang, Vivian Hu, Yizhu Jiao, Xuan Wang, and Jiawei Han. 2023b. Re-actIE: Enhancing chemical reaction extraction with weak supervision. In Findings of the Association for Computational Linguistics: ACL 2023, pages 12120– 12130, Toronto, Canada. Association for Computa… find
  46. Shaowen Zhou, Bowen Yu, Aixin Sun, Cheng Long, Jingyang Li, and Jian Sun. 2022. A survey on neural open information extraction: Current status and future directions. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22, pages 5694–5701. International… find
  47. Sizhe Zhou, Suyu Ge, Jiaming Shen, and Jiawei Han. 2023. Corpus-based relation extraction by identifying and refining relation patterns. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pages 20–38. Springer. find
  48. Sizhe Zhou, Yu Meng, Bowen Jin, and Jiawei Han. 2024. Grasping the essentials: Tailoring large language models for zero-shot relation extraction. Preprint, arXiv:2402.11142. find
  49. Jin Zhu, Mingyu Zhang, Yunyan Gai, Ronghua Zeng, Yuepeng Cai, and Dongsheng Lu. 2023. Quickly form stable cathode/electrolyte interface of lini0.5mn1.5o4 (lnmo)/graphite high-voltage lithium ion cells by using tosylmethyl isocyanide (tosmic) as electrolyte additive. Journal of Power Sources, 576:233… find
  50. Fu Zhang, He Liu, Zehan Li, and Jingwei Cheng. 2025. CE-DA: Custom embedding and dynamic aggregation for zero-shot relation extraction. In Proceedings of the 31st International Conference on Computational Linguistics, pages 9814–9823, Abu Dhabi, UAE. Association for Computational Linguistics. find
  51. Jun Zhao, WenYu Zhan, Xin Zhao, Qi Zhang, Tao Gui, Zhongyu Wei, Junzhe Wang, Minlong Peng, and Mingming Sun. 2023. RE-matching: A fine-grained semantic matching method for zero-shot relation extraction. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volum… find
  52. Guineng Zheng, Subhabrata Mukherjee, Xin Luna Dong, and Feifei Li. 2018. Opentag: Open attribute value extraction from product profiles. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery &; Data Mining, KDD ’18, page 1049–1058. ACM. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/xu-2026-zero-shot-open-schema-entity/