eprintid: 10205997 rev_number: 9 eprint_status: archive userid: 699 dir: disk0/10/20/59/97 datestamp: 2025-03-13 15:59:58 lastmod: 2025-03-13 15:59:58 status_changed: 2025-03-13 15:59:58 type: proceedings_section metadata_visibility: show sword_depositor: 699 creators_name: Li, Ziqing creators_name: Cukurova, Mutlu creators_name: Bulathwela, Sahan title: A Novel Approach to Scalable and Automatic Topic-Controlled Question Generation in Education ispublished: pub divisions: UCL divisions: B16 divisions: B04 divisions: B14 divisions: J77 divisions: F48 note: © 2025 Copyright held by the owner/author(s). This work is licensed under a Creative Commons Attribution 4.0 International License (https://creativecommons.org/licenses/by/4.0/). abstract: The development of Automatic Question Generation (QG) models has the potential to significantly improve educational practices by reducing the teacher workload associated with creating educational content. This paper introduces a novel approach to educational question generation that controls the topical focus of questions. The proposed Topic-Controlled Question Generation (T-CQG) method enhances the relevance and effectiveness of the generated content for educational purposes. Our approach uses fine-tuning on a pre-trained T5-small model, employing specially created datasets tailored to educational needs. The research further explores the impacts of pre-training strategies, quantisation, and data augmentation on the model’s performance. We specifically address the challenge of generating semantically aligned questions with paragraph-level contexts, thereby improving the topic specificity of the generated questions. In addition, we introduce and explore novel evaluation methods to assess the topical relatedness of the generated questions. Our results, validated through rigorous offline and human-backed evaluations, demonstrate that the proposed models effectively generate high-quality, topic-focused questions. These models have the potential to reduce teacher workload and support personalised tutoring systems by serving as bespoke question generators. With its relatively small number of parameters, the proposals not only advance the capabilities of question generation models for handling specific educational topics but also offer a scalable solution that reduces infrastructure costs. This scalability makes them feasible for widespread use in education without reliance on proprietary large language models like ChatGPT. date: 2025 date_type: published publisher: ACM official_url: https://doi.org/10.1145/3706468.3706487 oa_status: green full_text_type: pub language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 2364679 doi: 10.1145/3706468.3706487 isbn_13: 979-8-4007-0701-8 lyricists_name: Cukurova, Mutlu lyricists_name: Bulathwela, Sahan lyricists_id: MCUKU85 lyricists_id: MSSBU78 actors_name: Bulathwela, Sahan actors_id: MSSBU78 actors_role: owner full_text_status: public pres_type: paper publication: Proceedings of the 15th International Learning Analytics and Knowledge Conference pagerange: 148-158 event_title: LAK '25: The 15th International Learning Analytics and Knowledge Conference book_title: Proceedings of the 15th International Learning Analytics and Knowledge Conference citation: Li, Ziqing; Cukurova, Mutlu; Bulathwela, Sahan; (2025) A Novel Approach to Scalable and Automatic Topic-Controlled Question Generation in Education. In: Proceedings of the 15th International Learning Analytics and Knowledge Conference. (pp. pp. 148-158). ACM Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10205997/7/Bulathwela_A%20Novel%20Approach%20to%20Scalable%20and%20Automatic%20Topic-Controlled%20Question%20Generation%20in%20Education_VoR.pdf