{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T13:58:15Z","timestamp":1774360695062,"version":"3.50.1"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032212993","type":"print"},{"value":"9783032213006","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-21300-6_50","type":"book-chapter","created":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T13:05:21Z","timestamp":1774357521000},"page":"586-595","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Aligning Instruction-Tuned LLMs for\u00a0Event Extraction with\u00a0Multi-objective Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Omar","family":"Adjali","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0146-581X","authenticated-orcid":false,"given":"Siting","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7983-2384","authenticated-orcid":false,"given":"Omair Shahzad","family":"Bhatti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8857-8709","authenticated-orcid":false,"given":"Daniel","family":"Sonntag","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,25]]},"reference":[{"key":"50_CR1","unstructured":"Chu, T., et al.: SFT memorizes, RL generalizes: a comparative study of foundation model post-training. In: Forty-second International Conference on Machine Learning"},{"key":"50_CR2","unstructured":"Gao, J., Zhao, H., Wang, W., Yu, C., Xu, R.: EventRL: enhancing event extraction with outcome supervision for large language models. arXiv preprint arXiv:2402.11430 (2024)"},{"key":"50_CR3","unstructured":"Grattafiori, A., et\u00a0al.: The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)"},{"key":"50_CR4","doi-asserted-by":"crossref","unstructured":"Gui, H., et al.: IEPILE: unearthing large scale schema-conditioned information extraction corpus. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 127\u2013146 (2024)","DOI":"10.18653\/v1\/2024.acl-short.13"},{"key":"50_CR5","unstructured":"Hu, E.J., et al.: LoRA: Low-rank adaptation of large language models. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"50_CR6","doi-asserted-by":"crossref","unstructured":"Huang, K.H., et al.: TEXTEE: benchmark, reevaluation, reflections, and future challenges in event extraction. In: Findings of the Association for Computational Linguistics ACL 2024, pp. 12804\u201312825 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.760"},{"key":"50_CR7","unstructured":"Jiang, J., Wang, F., Shen, J., Kim, S., Kim, S.: A survey on large language models for code generation. arXiv preprint arXiv:2406.00515 (2024)"},{"key":"50_CR8","doi-asserted-by":"crossref","unstructured":"Jiao, Y., et al.: Instruct and extract: instruction tuning for on-demand information extraction. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 10030\u201310051 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.620"},{"key":"50_CR9","unstructured":"Jin, H., Lv, S., Wu, S., Hamdaqa, M.: Rl is neither a panacea nor a mirage: understanding supervised vs. reinforcement learning fine-tuning for LLMS. arXiv preprint arXiv:2508.16546 (2025)"},{"key":"50_CR10","unstructured":"Kim, J.D., Wang, Y., Yasunori, Y.: The genia event extraction shared task, 2013 edition-overview. In: Proceedings of the BioNLP Shared Task 2013 Workshop, pp. 8\u201315 (2013)"},{"key":"50_CR11","unstructured":"Kirk, R., et al.: Understanding the effects of RLHF on LLM generalisation and diversity. In: The Twelfth International Conference on Learning Representations"},{"key":"50_CR12","doi-asserted-by":"crossref","unstructured":"Li, P., et al.: CODEIE: large code generation models are better few-shot information extractors. In: The 61st Annual Meeting Of The Association For Computational Linguistics (2023)","DOI":"10.18653\/v1\/2023.acl-long.855"},{"key":"50_CR13","doi-asserted-by":"crossref","unstructured":"Li, S., Ji, H., Han, J.: Document-level event argument extraction by conditional generation. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 894\u2013908 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.69"},{"key":"50_CR14","doi-asserted-by":"crossref","unstructured":"Li, Z., et\u00a0al.: KnowCoder: coding structured knowledge into LLMS for universal information extraction. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 8758\u20138779 (2024)","DOI":"10.18653\/v1\/2024.acl-long.475"},{"key":"50_CR15","doi-asserted-by":"crossref","unstructured":"Lu, K., Pan, X., Song, K., Zhang, H., Yu, D., Chen, J.: PIVOINE: instruction tuning for open-world information extraction. arXiv preprint arXiv:2305.14898 (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.1009"},{"key":"50_CR16","unstructured":"Mirzadeh, S.I., Alizadeh, K., Shahrokhi, H., Tuzel, O., Bengio, S., Farajtabar, M.: GSM-symbolic: understanding the limitations of mathematical reasoning in large language models. In: The Thirteenth International Conference on Learning Representations"},{"key":"50_CR17","doi-asserted-by":"crossref","unstructured":"Qi, Y., Peng, H., Wang, X., Xu, B., Hou, L., Li, J.: ADELIE: aligning large language models on information extraction. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 7371\u20137387 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.419"},{"key":"50_CR18","unstructured":"Roziere, B., et\u00a0al.: Code llama: open foundation models for code. arXiv preprint arXiv:2308.12950 (2023)"},{"key":"50_CR19","unstructured":"Sainz, O., Garc\u00eda-Ferrero, I., Agerri, R., de\u00a0Lacalle, O.L., Rigau, G., Agirre, E.: Gollie: Annotation guidelines improve zero-shot information-extraction. In: The Twelfth International Conference on Learning Representations"},{"key":"50_CR20","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"50_CR21","unstructured":"Shao, Z., et\u00a0al.: DeepSeekMath: pushing the limits of mathematical reasoning in open language models 2(3), 5 (2024). arXiv:2402.03300 (2024)"},{"key":"50_CR22","doi-asserted-by":"publisher","unstructured":"Srivastava, S., Pati, S., Yao, Z.: Instruction-tuning LLMs for event extraction with annotation guidelines. In: Che, W., Nabende, J., Shutova, E., Pilehvar, M.T. (eds.) Findings of the Association for Computational Linguistics: ACL 2025, pp. 13055\u201313071. Association for Computational Linguistics, Vienna, Austria (2025). https:\/\/doi.org\/10.18653\/v1\/2025.findings-acl.677, https:\/\/aclanthology.org\/2025.findings-acl.677\/","DOI":"10.18653\/v1\/2025.findings-acl.677"},{"key":"50_CR23","doi-asserted-by":"crossref","unstructured":"Sun, Z., et al.: PHEE: a dataset for pharmacovigilance event extraction from text. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 5571\u20135587 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.376"},{"key":"50_CR24","unstructured":"Wang, X., et\u00a0al.: Instructuie: multi-task instruction tuning for unified information extraction. arXiv preprint arXiv:2304.08085 (2023)"},{"key":"50_CR25","doi-asserted-by":"crossref","unstructured":"Wang, X., Li, S., Ji, H.: Code4Struct: code generation for few-shot event structure prediction. In: The 61st Annual Meeting Of The Association For Computational Linguistics (2023)","DOI":"10.18653\/v1\/2023.acl-long.202"},{"key":"50_CR26","unstructured":"von Werra, L., et al.: TRL: Transformer Reinforcement Learning (2020). https:\/\/github.com\/huggingface\/trl"}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-21300-6_50","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T13:05:44Z","timestamp":1774357544000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-21300-6_50"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032212993","9783032213006"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-21300-6_50","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"25 March 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ECIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Delft","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 March 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 April 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"48","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecir2026.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}