{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T18:23:59Z","timestamp":1780597439607,"version":"3.54.1"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031643019","type":"print"},{"value":"9783031643026","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-64302-6_30","type":"book-chapter","created":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T06:04:39Z","timestamp":1719813879000},"page":"424-438","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Fine-Tuning a\u00a0Large Language Model with\u00a0Reinforcement Learning for\u00a0Educational Question Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8789-5713","authenticated-orcid":false,"given":"Salima","family":"Lamsiyah","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4281-2472","authenticated-orcid":false,"given":"Abdelkader","family":"El Mahdaouy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2233-3155","authenticated-orcid":false,"given":"Aria","family":"Nourbakhsh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0308-7637","authenticated-orcid":false,"given":"Christoph","family":"Schommer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,7,2]]},"reference":[{"key":"30_CR1","doi-asserted-by":"publisher","unstructured":"Bulathwela, S., Muse, H., Yilmaz, E.: Scalable educational question generation with pre-trained language models. In: International Conference on Artificial Intelligence in Education, pp. 327\u2013339. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-36272-9_27","DOI":"10.1007\/978-3-031-36272-9_27"},{"key":"30_CR2","unstructured":"Chen, Y., Wu, L., Zaki, M.J.: Reinforcement learning based graph-to-sequence model for natural question generation. arXiv preprint arXiv:1908.04942 (2019)"},{"key":"30_CR3","unstructured":"Danon, G., Last, M.: A syntactic approach to domain-specific automatic question generation. arXiv preprint arXiv:1712.09827 (2017)"},{"issue":"1","key":"30_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s41039-021-00151-1","volume":"16","author":"B Das","year":"2021","unstructured":"Das, B., Majumder, M., Phadikar, S., Sekh, A.A.: Automatic question generation and answer assessment: a survey. Res. Pract. Technol. Enhanc. Learn. 16(1), 1\u201315 (2021)","journal-title":"Res. Pract. Technol. Enhanc. Learn."},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Du, X., Shao, J., Cardie, C.: Learning to ask: neural question generation for reading comprehension. In: Barzilay, R., Kan, M.Y. (eds.) Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1342\u20131352 (2017)","DOI":"10.18653\/v1\/P17-1123"},{"key":"30_CR6","doi-asserted-by":"publisher","unstructured":"Elkins, S., Kochmar, E., Serban, I., Cheung, J.C.: How useful are educational questions generated by large language models? In: International Conference on Artificial Intelligence in Education, pp. 536\u2013542. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-36336-8_83","DOI":"10.1007\/978-3-031-36336-8_83"},{"key":"30_CR7","doi-asserted-by":"crossref","unstructured":"Gao, T., Yao, X., Chen, D.: SimCSE: simple contrastive learning of sentence embeddings. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 6894\u20136910 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"30_CR8","doi-asserted-by":"crossref","unstructured":"Gou, Q., et al.: Diversify question generation with retrieval-augmented style transfer. In: Bouamor, H., Pino, J., Bali, K. (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 1677\u20131690. Association for Computational Linguistics (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.104"},{"issue":"2","key":"30_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103232","volume":"60","author":"M Guan","year":"2023","unstructured":"Guan, M., Mondal, S.K., Dai, H.N., Bao, H.: Reinforcement learning-driven deep question generation with rich semantics. Inf. Process. Manage. 60(2), 103232 (2023)","journal-title":"Inf. Process. Manage."},{"key":"30_CR10","unstructured":"Heilman, M., Smith, N.A.: Good question! statistical ranking for question generation. In: Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pp. 609\u2013617 (2010)"},{"key":"30_CR11","doi-asserted-by":"publisher","unstructured":"Jiao, Y., Shridhar, K., Cui, P., Zhou, W., Sachan, M.: Automatic educational question generation with difficulty level controls. In: International Conference on Artificial Intelligence in Education, pp. 476\u2013488. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-36272-9_39","DOI":"10.1007\/978-3-031-36272-9_39"},{"issue":"7","key":"30_CR12","first-page":"2469","volume":"31","author":"Y Keneshloo","year":"2019","unstructured":"Keneshloo, Y., Shi, T., Ramakrishnan, N., Reddy, C.K.: Deep reinforcement learning for sequence-to-sequence models. IEEE Trans. Neural Netw. Learn. Syst. 31(7), 2469\u20132489 (2019)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"Kumar, V., Ramakrishnan, G., Li, Y.F.: Putting the Horse Before the Cart: a generator-evaluator framework for question generation from text. In: Bansal, M., Villavicencio, A. (eds.) Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), pp. 812\u2013821 (2019)","DOI":"10.18653\/v1\/K19-1076"},{"key":"30_CR14","doi-asserted-by":"publisher","unstructured":"Lamsiyah, S., Schommer, C.: A comparative study of sentence embeddings for unsupervised extractive multi-document summarization. In: Benelux Conference on Artificial Intelligence, pp. 78\u201395. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-39144-6_6","DOI":"10.1007\/978-3-031-39144-6_6"},{"key":"30_CR15","doi-asserted-by":"publisher","unstructured":"Leite, B., Cardoso, H.L.: Towards enriched controllability for educational question generation. In: International Conference on Artificial Intelligence in Education, pp. 786\u2013791. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-36272-9_72","DOI":"10.1007\/978-3-031-36272-9_72"},{"key":"30_CR16","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Lo, K., Wang, L.L., Neumann, M., Kinney, R., Weld, D.: S2ORC: the semantic scholar open research corpus. In: Jurafsky, D., Chai, J., Schluter, N., Tetreault, J. (eds.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 4969\u20134983 (2020)","DOI":"10.18653\/v1\/2020.acl-main.447"},{"key":"30_CR18","doi-asserted-by":"crossref","unstructured":"Mostafazadeh, N., Misra, I., Devlin, J., Mitchell, M., He, X., Vanderwende, L.: Generating natural questions about an image. arXiv preprint arXiv:1603.06059 (2016)","DOI":"10.18653\/v1\/P16-1170"},{"key":"30_CR19","doi-asserted-by":"crossref","unstructured":"Naeiji, A., An, A., Davoudi, H., Delpisheh, M., Alzghool, M.: Question generation using sequence-to-sequence model with semantic role labels. In: Vlachos, A., Augenstein, I. (eds.) Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pp. 2830\u20132842 (2023)","DOI":"10.18653\/v1\/2023.eacl-main.207"},{"key":"30_CR20","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Isabelle, P., Charniak, E., Lin, D. (eds.) Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"30_CR21","unstructured":"Paulus, R., Xiong, C., Socher, R.: A deep reinforced model for abstractive summarization. arXiv preprint arXiv:1705.04304 (2017)"},{"key":"30_CR22","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1) (2020)"},{"key":"30_CR23","doi-asserted-by":"crossref","unstructured":"Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: SQuAD: 100,000+ questions for machine comprehension of text. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 2383\u20132392 (2016)","DOI":"10.18653\/v1\/D16-1264"},{"key":"30_CR24","doi-asserted-by":"crossref","unstructured":"Rennie, S.J., Marcheret, E., Mroueh, Y., Ross, J., Goel, V.: Self-critical sequence training for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7008\u20137024 (2017)","DOI":"10.1109\/CVPR.2017.131"},{"key":"30_CR25","unstructured":"Rus, V., Cai, Z., Graesser, A.: Question generation: example of a multi-year evaluation campaign. In: Proceedings of WS on the QGSTEC (2008)"},{"key":"30_CR26","doi-asserted-by":"crossref","unstructured":"Serban, I.V., et al.: Generating factoid questions with recurrent neural networks: the 30M factoid question-answer corpus. In: Erk, K., Smith, N.A. (eds.) Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 588\u2013598 (2016)","DOI":"10.18653\/v1\/P16-1056"},{"key":"30_CR27","doi-asserted-by":"publisher","unstructured":"Shimmei, M., Bier, N., Matsuda, N.: Machine-generated questions attract instructors when acquainted with learning objectives. In: International Conference on Artificial Intelligence in Education, pp. 3\u201315. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-36272-9_1","DOI":"10.1007\/978-3-031-36272-9_1"},{"key":"30_CR28","unstructured":"Song, L., Wang, Z., Hamza, W.: A unified query-based generative model for question generation and question answering. arXiv preprint arXiv:1709.01058 (2017)"},{"key":"30_CR29","doi-asserted-by":"crossref","unstructured":"Song, L., Wang, Z., Hamza, W., Zhang, Y., Gildea, D.: Leveraging context information for natural question generation. In: Walker, M., Ji, H., Stent, A. (eds.) Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 2 (Short Papers), pp. 569\u2013574 (2018)","DOI":"10.18653\/v1\/N18-2090"},{"key":"30_CR30","doi-asserted-by":"crossref","unstructured":"Wang, L., Xu, Z., Lin, Z., Zheng, H., Shen, Y.: Answer-driven deep question generation based on reinforcement learning. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 5159\u20135170 (2020)","DOI":"10.18653\/v1\/2020.coling-main.452"},{"key":"30_CR31","doi-asserted-by":"crossref","unstructured":"Welbl, J., Liu, N.F., Gardner, M.: Crowdsourcing multiple choice science questions. In: Derczynski, L., Xu, W., Ritter, A., Baldwin, T. (eds.) Proceedings of the 3rd Workshop on Noisy User-generated Text, pp. 94\u2013106 (2017)","DOI":"10.18653\/v1\/W17-4413"},{"key":"30_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, Z.: Improved Adam optimizer for deep neural networks. In: 2018 IEEE\/ACM 26th International Symposium on Quality of Service (IWQoS), pp.\u00a01\u20132. IEEE (2018)","DOI":"10.1109\/IWQoS.2018.8624183"},{"key":"30_CR33","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Hou, Y., Wang, D., Yu, M., Liu, C., Ma, X.: Educational question generation of children storybooks via question type distribution learning and event-centric summarization. In: Muresan, S., Nakov, P., Villavicencio, A. (eds.) Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 5073\u20135085 (2022)","DOI":"10.18653\/v1\/2022.acl-long.348"},{"key":"30_CR34","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"662","DOI":"10.1007\/978-3-319-73618-1_56","volume-title":"Natural Language Processing and Chinese Computing","author":"Q Zhou","year":"2018","unstructured":"Zhou, Q., Yang, N., Wei, F., Tan, C., Bao, H., Zhou, M.: Neural question generation from text: a preliminary study. In: Huang, X., Jiang, J., Zhao, D., Feng, Y., Hong, Yu. (eds.) NLPCC 2017. LNCS (LNAI), vol. 10619, pp. 662\u2013671. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-73618-1_56"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence in Education"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-64302-6_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T20:30:51Z","timestamp":1757104251000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-64302-6_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031643019","9783031643026"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-64302-6_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"2 July 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AIED","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Intelligence in Education","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Recife","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazil","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 July 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 July 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aied2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aied2024.cesar.school\/home","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}