{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T11:21:42Z","timestamp":1765279302639,"version":"3.41.0"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031945748","type":"print"},{"value":"9783031945755","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-94575-5_6","type":"book-chapter","created":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T02:14:44Z","timestamp":1748657684000},"page":"94-115","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Kastor: Fine-Tuned Small Language Models for\u00a0Shape-Based Active Relation Extraction"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7302-9037","authenticated-orcid":false,"given":"C\u00e9lian","family":"Ringwald","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0543-1232","authenticated-orcid":false,"given":"Fabien","family":"Gandon","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5959-5561","authenticated-orcid":false,"given":"Catherine","family":"Faron","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9064-0463","authenticated-orcid":false,"given":"Franck","family":"Michel","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9829-7401","authenticated-orcid":false,"given":"Hanna","family":"Abi Akl","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,1]]},"reference":[{"key":"6_CR1","doi-asserted-by":"publisher","unstructured":"Alt, C., Gabryszak, A., Hennig, L.: TACRED revisited: a thorough evaluation of the TACRED relation extraction task. In: Jurafsky, D., Chai, J., Schluter, N., Tetreault, J. (eds.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 1558\u20131569. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.142","DOI":"10.18653\/v1\/2020.acl-main.142"},{"key":"6_CR2","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1007\/978-3-319-13704-9_3","volume-title":"Knowledge Engineering and Knowledge Management","author":"I Augenstein","year":"2014","unstructured":"Augenstein, I., Maynard, D., Ciravegna, F.: Relation extraction from the web using distant supervision. In: Janowicz, K., Schlobach, S., Lambrix, P., Hyv\u00f6nen, E. (eds.) Knowledge Engineering and Knowledge Management, pp. 26\u201341. Springer, Cham (2014)"},{"key":"6_CR3","doi-asserted-by":"publisher","unstructured":"Dligach, D., Bethard, S., Miller, T., Savova, G.: Exploring text representations for generative temporal relation extraction. In: Naumann, T., Bethard, S., Roberts, K., Rumshisky, A. (eds.) Proceedings of the 4th Clinical Natural Language Processing Workshop, pp. 109\u2013113. Association for Computational Linguistics, Seattle (2022). https:\/\/doi.org\/10.18653\/v1\/2022.clinicalnlp-1.12","DOI":"10.18653\/v1\/2022.clinicalnlp-1.12"},{"key":"6_CR4","unstructured":"Efeoglu, S., Paschke, A.: Retrieval-augmented generation-based relation extraction. ArXiv abs\/2404.13397 (2024). https:\/\/api.semanticscholar.org\/CorpusID:269292881"},{"key":"6_CR5","unstructured":"Gallardo, A.P., Consoli, S., Ceresa, M., Hulsman, R., Bertolini, L.: On constructing biomedical text-to-graph systems with large language models. In: Tiwari, S., et al. (eds.) Joint proceedings of the 3rd International workshop on knowledge graph generation from text (TEXT2KG) and Data Quality meets Machine Learning and Knowledge Graphs (DQMLKG) Co-located with the Extended Semantic Web Conference ( ESWC 2024), Hersonissos, Greece, 26\u201330 May 2024. CEUR Workshop Proceedings, vol.\u00a03747, p.\u00a012. CEUR-WS.org (2024). https:\/\/ceur-ws.org\/Vol-3747\/text2kg_paper10.pdf"},{"key":"6_CR6","doi-asserted-by":"publisher","unstructured":"Geng, S., Josifoski, M., Peyrard, M., West, R.: Grammar-constrained decoding for structured NLP tasks without finetuning. In: Bouamor, H., Pino, J., Bali, K. (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 10932\u201310952. Association for Computational Linguistics, Singapore (2023). https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.674, https:\/\/aclanthology.org\/2023.emnlp-main.674\/","DOI":"10.18653\/v1\/2023.emnlp-main.674"},{"key":"6_CR7","unstructured":"Grangier, D., Katharopoulos, A., Ablin, P., Hannun, A.: Need a small specialized language model? Plan early! (2024). https:\/\/arxiv.org\/abs\/2402.01093"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Hofer, M., Obraczka, D., Saeedi, A., K\u00f6pcke, H., Rahm, E.: Construction of knowledge graphs: state and challenges (2023). https:\/\/arxiv.org\/abs\/2302.11509","DOI":"10.2139\/ssrn.4605059"},{"key":"6_CR9","unstructured":"Huang, L., et al.: A survey on hallucination in large language models: principles, taxonomy, challenges, and open questions (2023). https:\/\/arxiv.org\/abs\/2311.05232"},{"key":"6_CR10","doi-asserted-by":"publisher","unstructured":"Huguet\u00a0Cabot, P.L., Tedeschi, S., Ngonga\u00a0Ngomo, A.C., Navigli, R.: RED$$^{\\rm fm}$$: a filtered and multilingual relation extraction dataset. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 4326\u20134343. Association for Computational Linguistics, Toronto (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.237","DOI":"10.18653\/v1\/2023.acl-long.237"},{"key":"6_CR11","doi-asserted-by":"publisher","unstructured":"Huguet\u00a0Cabot, P.L., Navigli, R.: REBEL: relation extraction by end-to-end language generation. In: Moens, M.F., Huang, X., Specia, L., Yih, S.W.t. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2021, pp. 2370\u20132381. Association for Computational Linguistics, Punta Cana (2021). https:\/\/doi.org\/10.18653\/v1\/2021.findings-emnlp.204","DOI":"10.18653\/v1\/2021.findings-emnlp.204"},{"key":"6_CR12","unstructured":"Hussam\u00a0Ghanem, C.C.: Fine-tuning vs. prompting: evaluating the knowledge graph construction with LLMs (2024). https:\/\/ceur-ws.org\/Vol-3747\/text2kg_paper7.pdf"},{"issue":"12","key":"6_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3571730","volume":"55","author":"Z Ji","year":"2023","unstructured":"Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y.J., Madotto, A., Fung, P.: Survey of hallucination in natural language generation. ACM Comput. Surv. 55(12), 1\u201338 (2023). https:\/\/doi.org\/10.1145\/3571730","journal-title":"ACM Comput. Surv."},{"key":"6_CR14","doi-asserted-by":"publisher","unstructured":"Josifoski, M., De\u00a0Cao, N., Peyrard, M., Petroni, F., West, R.: GenIE: generative information extraction. In: Carpuat, M., de\u00a0Marneffe, M.C., Meza\u00a0Ruiz, I.V. (eds.) Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 4626\u20134643. Association for Computational Linguistics, Seattle (2022). https:\/\/doi.org\/10.18653\/v1\/2022.naacl-main.342, https:\/\/aclanthology.org\/2022.naacl-main.342","DOI":"10.18653\/v1\/2022.naacl-main.342"},{"key":"6_CR15","unstructured":"Kandpal, N., Deng, H., Roberts, A., Wallace, E., Raffel, C.: Large language models struggle to learn long-tail knowledge. In: Proceedings of the 40th International Conference on Machine Learning, ICML 2023. JMLR.org (2023)"},{"key":"6_CR16","doi-asserted-by":"publisher","unstructured":"Lehmann, J., et al.: Large language models for scientific question answering: an extensive analysis of the sciqa benchmark. In: Mero\u00f1o-Pe\u00f1uela, A., et al. (eds.) ESWC 2024, Part I. LNCS, vol. 14664, pp. 199\u2013217. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-60626-7_11","DOI":"10.1007\/978-3-031-60626-7_11"},{"key":"6_CR17","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1007\/978-3-031-60626-7_11","volume-title":"The Semantic Web","author":"J Lehmann","year":"2024","unstructured":"Lehmann, J., et al.: Large language models for scientific question answering: an extensive analysis of the sciqa benchmark. In: Mero\u00f1o Pe\u00f1uela, A., et al. (eds.) The Semantic Web, pp. 199\u2013217. Springer, Cham (2024)"},{"key":"6_CR18","unstructured":"Li, B., et al.: Evaluating chatGPT\u2019s information extraction capabilities: an assessment of performance, explainability, calibration, and faithfulness. ArXiv abs\/2304.11633 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258297899"},{"key":"6_CR19","doi-asserted-by":"publisher","unstructured":"Li, D., et al.: Overcoming catastrophic forgetting during domain adaptation of seq2seq language generation. In: Carpuat, M., de\u00a0Marneffe, M.C., Meza\u00a0Ruiz, I.V. (eds.) Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 5441\u20135454. Association for Computational Linguistics, Seattle (2022). https:\/\/doi.org\/10.18653\/v1\/2022.naacl-main.398","DOI":"10.18653\/v1\/2022.naacl-main.398"},{"key":"6_CR20","doi-asserted-by":"publisher","unstructured":"Li, G., et al.: Recall, retrieve and reason: towards better in-context relation extraction. In: Larson, K. (ed.) Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI-24, pp. 6368\u20136376. International Joint Conferences on Artificial Intelligence Organization (2024). https:\/\/doi.org\/10.24963\/ijcai.2024\/704","DOI":"10.24963\/ijcai.2024\/704"},{"key":"6_CR21","doi-asserted-by":"publisher","unstructured":"Li, M., Shi, T., Ziems, C., Kan, M.Y., Chen, N., Liu, Z., Yang, D.: CoAnnotating: uncertainty-guided work allocation between human and large language models for data annotation. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (2023). https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.92","DOI":"10.18653\/v1\/2023.emnlp-main.92"},{"key":"6_CR22","doi-asserted-by":"publisher","unstructured":"Liu, Y., Li, D., Wang, K., Xiong, Z., Shi, F., Wang, J., Li, B., Hang, B.: Are LLMs good at structured outputs? A benchmark for evaluating structured output capabilities in LLMs. Inf. Process. Manage. 61(5), 103809 (2024). https:\/\/doi.org\/10.1016\/j.ipm.2024.103809, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0306457324001687","DOI":"10.1016\/j.ipm.2024.103809"},{"key":"6_CR23","unstructured":"Lu, Z., et al.: Small language models: survey, measurements, and insights (2024). https:\/\/arxiv.org\/abs\/2409.15790"},{"key":"6_CR24","doi-asserted-by":"publisher","unstructured":"Ma, Y., Wang, A., Okazaki, N.: DREEAM: guiding attention with evidence for improving document-level relation extraction. In: Vlachos, A., Augenstein, I. (eds.) Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pp. 1971\u20131983. Association for Computational Linguistics, Dubrovnik (2023).https:\/\/doi.org\/10.18653\/v1\/2023.eacl-main.145","DOI":"10.18653\/v1\/2023.eacl-main.145"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"van\u00a0der Meer, M., Falk, N., Murukannaiah, P.K., Liscio, E.: Annotator-centric active learning for subjective NLP tasks (2024). https:\/\/arxiv.org\/abs\/2404.15720","DOI":"10.18653\/v1\/2024.emnlp-main.1031"},{"key":"6_CR26","unstructured":"Paolini, G., et al.: Structured prediction as translation between augmented natural languages (2021). https:\/\/arxiv.org\/abs\/2101.05779"},{"key":"6_CR27","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1007\/978-3-031-78952-6_8","volume-title":"The Semantic Web: ESWC 2024 Satellite Events","author":"C Ringwald","year":"2025","unstructured":"Ringwald, C., Gandon, F., Faron, C., Michel, F., Akl, H.A.: 12 shades of RDF: impact of syntaxes on data extraction with language models. In: Mero\u00f1o Pe\u00f1uela, A., et al. (eds.) The Semantic Web: ESWC 2024 Satellite Events, pp. 81\u201391. Springer, Cham (2025)"},{"key":"6_CR28","unstructured":"Rogulsky, S., Popovic, N., F\u00e4rber, M.: The effects of hallucinations in synthetic training data for relation extraction. arxiv (2024)"},{"key":"6_CR29","unstructured":"Rossiello, G., Chowdhury, M.F.M., Mihindukulasooriya, N., Cornec, O., Gliozzo, A.M.: KnowGL: knowledge generation and linking from text (2022). https:\/\/arxiv.org\/abs\/2210.13952"},{"key":"6_CR30","doi-asserted-by":"publisher","first-page":"100679","DOI":"10.1016\/j.websem.2021.100679","volume":"72","author":"K Shenoy","year":"2022","unstructured":"Shenoy, K., Ilievski, F., Garijo, D., Schwabe, D., Szekely, P.: A study of the quality of wikidata. J. Web Semant. 72, 100679 (2022). https:\/\/doi.org\/10.1016\/j.websem.2021.100679","journal-title":"J. Web Semant."},{"key":"6_CR31","doi-asserted-by":"publisher","unstructured":"Smirnova, A., Cudr\u00e9-Mauroux, P.: Relation extraction using distant supervision: a survey. ACM Comput. Surv. 51(5) (2018).https:\/\/doi.org\/10.1145\/3241741","DOI":"10.1145\/3241741"},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Stoica, G., Platanios, E.A., P\u2019oczos, B.: Re-TACRED: addressing shortcomings of the tacred dataset. In: AAAI Conference on Artificial Intelligence (2021). https:\/\/api.semanticscholar.org\/CorpusID:233296843","DOI":"10.1609\/aaai.v35i15.17631"},{"key":"6_CR33","doi-asserted-by":"publisher","unstructured":"Taill\u00e9, B., Guigue, V., Scoutheeten, G., Gallinari, P.: Let\u2019s stop incorrect comparisons in end-to-end relation extraction! In: Webber, B., Cohn, T., He, Y., Liu, Y. (eds.) Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 3689\u20133701. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.301","DOI":"10.18653\/v1\/2020.emnlp-main.301"},{"key":"6_CR34","doi-asserted-by":"publisher","unstructured":"Tsaneva, S., Sabou, M.: Enhancing human-in-the-loop ontology curation results through task design. ACM J. Data Inf. Qual. 16(1), 4:1\u20134:25 (2024). https:\/\/doi.org\/10.1145\/3626960","DOI":"10.1145\/3626960"},{"key":"6_CR35","doi-asserted-by":"publisher","unstructured":"Wadhwa, S., Amir, S., Wallace, B.: Revisiting relation extraction in the era of large language models. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 15566\u201315589. Association for Computational Linguistics, Toronto (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.868","DOI":"10.18653\/v1\/2023.acl-long.868"},{"key":"6_CR36","unstructured":"Wang, F., et al.: A comprehensive survey of small language models in the era of large language models: techniques, enhancements, applications, collaboration with LLMs, and trustworthiness (2024). https:\/\/arxiv.org\/abs\/2411.03350"},{"key":"6_CR37","doi-asserted-by":"publisher","unstructured":"Yao, Y., et al.: CodRED: a cross-document relation extraction dataset for acquiring knowledge in the wild. In: Moens, M.F., Huang, X., Specia, L., Yih, S.W.t. (eds.) Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 4452\u20134472. Association for Computational Linguistics, Online and Punta Cana (2021). https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.366","DOI":"10.18653\/v1\/2021.emnlp-main.366"},{"key":"6_CR38","doi-asserted-by":"publisher","unstructured":"Yao, Y., et al.: DocRED: a large-scale document-level relation extraction dataset. In: Korhonen, A., Traum, D., M\u00e0rquez, L. (eds.) Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 764\u2013777. Association for Computational Linguistics, Florence (2019). https:\/\/doi.org\/10.18653\/v1\/P19-1074","DOI":"10.18653\/v1\/P19-1074"},{"key":"6_CR39","doi-asserted-by":"publisher","unstructured":"Zaratiana, U., Tomeh, N., Holat, P., Charnois, T.: GLiNER: generalist model for named entity recognition using bidirectional transformer. In: Duh, K., Gomez, H., Bethard, S. (eds.) Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pp. 5364\u20135376. Association for Computational Linguistics, Mexico City (2024). https:\/\/doi.org\/10.18653\/v1\/2024.naacl-long.300","DOI":"10.18653\/v1\/2024.naacl-long.300"},{"key":"6_CR40","unstructured":"Zhang, B., Reklos, I., Jain, N., Pe\u00f1uela, A.M., Simperl, E.: Using large language models for knowledge engineering (LLMKE): a case study on wikidata (2023). https:\/\/arxiv.org\/abs\/2309.08491"},{"key":"6_CR41","unstructured":"Zheng, L., et al.: Judging LLM-as-a-judge with MT-bench and chatbot arena (2023). https:\/\/arxiv.org\/abs\/2306.05685"}],"container-title":["Lecture Notes in Computer Science","The Semantic Web"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-94575-5_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T02:15:03Z","timestamp":1748657703000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-94575-5_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031945748","9783031945755"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-94575-5_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"1 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ESWC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Semantic Web Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portoroz","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Slovenia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"esws2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2025.eswc-conferences.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}