{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T08:20:16Z","timestamp":1787818816485,"version":"build-2784847793"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031992636","type":"print"},{"value":"9783031992643","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\/978-3-031-99264-3_22","type":"book-chapter","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T06:43:31Z","timestamp":1753253011000},"page":"177-184","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LLM Agents for\u00a0Verifiable Question Generation and\u00a0Grading"],"prefix":"10.1007","author":[{"given":"Jacob","family":"Levine","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matt","family":"West","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mariana","family":"Silva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,21]]},"reference":[{"key":"22_CR1","doi-asserted-by":"publisher","unstructured":"Bang, Y., et al.: A Multitask, multilingual, multimodal evaluation of ChatGPT on reasoning, hallucination, and interactivity (2023). https:\/\/doi.org\/10.48550\/arXiv.2302.04023. arXiv:2302.04023 [cs]","DOI":"10.48550\/arXiv.2302.04023"},{"key":"22_CR2","doi-asserted-by":"publisher","unstructured":"Emeka, C., Smith, D., Zilles, C., West, M., Herman, G., Bretl, T.: Determining the best policies for second-chance tests for STEM students. In: 2023 ASEE Annual Conference & Exposition Proceedings, p. 43019. ASEE Conferences, Baltimore (2023). https:\/\/doi.org\/10.18260\/1-2-43019","DOI":"10.18260\/1-2-43019"},{"issue":"1","key":"22_CR3","doi-asserted-by":"publisher","first-page":"8","DOI":"10.4219\/jaa-2007-704","volume":"19","author":"TR Guskey","year":"2007","unstructured":"Guskey, T.R.: Closing achievement gaps: revisiting Benjamin S. Bloom\u2019s, \u201cLearning for Mastery\u2019\u2019. J. Adv. Acad. 19(1), 8\u201331 (2007). https:\/\/doi.org\/10.4219\/jaa-2007-704","journal-title":"J. Adv. Acad."},{"key":"22_CR4","doi-asserted-by":"publisher","unstructured":"Joshi, H., Cambronero, J., Gulwani, S., Le, V., Radicek, I., Verbruggen, G.: Repair is nearly generation: multilingual program repair with LLMs (2022). https:\/\/doi.org\/10.48550\/arXiv.2208.11640. arXiv:2208.11640","DOI":"10.48550\/arXiv.2208.11640"},{"key":"22_CR5","doi-asserted-by":"publisher","unstructured":"Kim, T.S., Choi, D., Choi, Y., Kim, J.: Stylette: styling the web with natural language. In: CHI Conference on Human Factors in Computing Systems, pp. 1\u201317. ACM, New Orleans (2022). https:\/\/doi.org\/10.1145\/3491102.3501931","DOI":"10.1145\/3491102.3501931"},{"key":"22_CR6","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. In: Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS \u201920. Curran Associates Inc., Red Hook (2020)"},{"key":"22_CR7","doi-asserted-by":"publisher","unstructured":"Li, J., Yuan, Y., Zhang, Z.: Enhancing LLM factual accuracy with RAG to counter hallucinations: a case study on domain-specific queries in private knowledge-bases (2024). https:\/\/doi.org\/10.48550\/arXiv.2403.10446. arXiv:2403.10446","DOI":"10.48550\/arXiv.2403.10446"},{"key":"22_CR8","doi-asserted-by":"publisher","unstructured":"Liang, P., et al.: Holistic evaluation of language models (2023). https:\/\/doi.org\/10.48550\/arXiv.2211.09110. arXiv:2211.09110","DOI":"10.48550\/arXiv.2211.09110"},{"key":"22_CR9","doi-asserted-by":"publisher","unstructured":"Liventsev, V., Grishina, A., H\u00e4rm\u00e4, A., Moonen, L.: Fully autonomous programming with large language models. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 1146\u20131155 (2023). https:\/\/doi.org\/10.1145\/3583131.3590481. arXiv:2304.10423","DOI":"10.1145\/3583131.3590481"},{"key":"22_CR10","doi-asserted-by":"publisher","unstructured":"Lopez-Lira, A., Tang, Y.: Can ChatGPT forecast stock price movements? return predictability and large language models (2024). https:\/\/doi.org\/10.48550\/arXiv.2304.07619. arXiv:2304.07619","DOI":"10.48550\/arXiv.2304.07619"},{"key":"22_CR11","doi-asserted-by":"publisher","unstructured":"Lu, S., Duan, N., Han, H., Guo, D., Hwang, S.w., Svyatkovskiy, A.: ReACC: a retrieval-augmented code completion framework (2022). https:\/\/doi.org\/10.48550\/arXiv.2203.07722. arXiv:2203.07722","DOI":"10.48550\/arXiv.2203.07722"},{"key":"22_CR12","doi-asserted-by":"publisher","unstructured":"Luo, Z., et al.: WizardCoder: empowering code large language models with evol-instruct (2023). https:\/\/doi.org\/10.48550\/arXiv.2306.08568. arXiv:2306.08568","DOI":"10.48550\/arXiv.2306.08568"},{"key":"22_CR13","doi-asserted-by":"publisher","unstructured":"Maynez, J., Narayan, S., Bohnet, B., McDonald, R.: On faithfulness and factuality in abstractive summarization. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 1906\u20131919. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.173","DOI":"10.18653\/v1\/2020.acl-main.173"},{"key":"22_CR14","unstructured":"Parsons, D., Haden, P.: Parson\u2019s programming puzzles: a fun and effective learning tool for first programming courses. In: Proceedings of the 8th Australasian Conference on Computing Education, ACE \u201906, vol. 52, pp. 157\u2013163. Australian Computer Society, Inc. (2006)"},{"key":"22_CR15","doi-asserted-by":"publisher","unstructured":"Parvez, M.R., Ahmad, W.U., Chakraborty, S., Ray, B., Chang, K.W.: Retrieval augmented code generation and summarization (2021). https:\/\/doi.org\/10.48550\/arXiv.2108.11601, arXiv:2108.11601","DOI":"10.48550\/arXiv.2108.11601"},{"key":"22_CR16","doi-asserted-by":"publisher","unstructured":"Poulsen, S., Gertner, Y., Cosman, B., West, M., Herman, G.L.: Efficiency of learning from proof blocks versus writing proofs. In: Proceedings of the 54th ACM Technical Symposium on Computer Science Education, SIGCSE 2023, vol. 1, pp. 472\u2013478. Association for Computing Machinery, New York (2023). https:\/\/doi.org\/10.1145\/3545945.3569797","DOI":"10.1145\/3545945.3569797"},{"key":"22_CR17","doi-asserted-by":"publisher","unstructured":"Rozi\u00e8re, B., et al.: Code llama: open foundation models for code (2024). https:\/\/doi.org\/10.48550\/arXiv.2308.12950. arXiv:2308.12950","DOI":"10.48550\/arXiv.2308.12950"},{"key":"22_CR18","doi-asserted-by":"publisher","unstructured":"Shuster, K., Poff, S., Chen, M., Kiela, D., Weston, J.: Retrieval Augmentation reduces hallucination in conversation. In: Findings of the Association for Computational Linguistics: EMNLP 2021, pp. 3784\u20133803. Association for Computational Linguistics, Punta Cana (2021). https:\/\/doi.org\/10.18653\/v1\/2021.findings-emnlp.320","DOI":"10.18653\/v1\/2021.findings-emnlp.320"},{"key":"22_CR19","doi-asserted-by":"publisher","unstructured":"Verma, A., Bretl, T., West, M., Zilles, C.: A quantitative analysis of when students choose to grade questions on computerized exams with multiple attempts. In: Proceedings of the Seventh ACM Conference on Learning @ Scale, pp. 329\u2013332. ACM, Virtual Event (2020). https:\/\/doi.org\/10.1145\/3386527.3406740","DOI":"10.1145\/3386527.3406740"},{"key":"22_CR20","doi-asserted-by":"publisher","unstructured":"Wei, A., Haghtalab, N., Steinhardt, J.: Jailbroken: how does LLM safety training fail? In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. (eds.) Advances in Neural Information Processing Systems, vol.\u00a036, pp. 80079\u201380110. Curran Associates, Inc. (2023). https:\/\/doi.org\/10.5555\/3666122.3669630","DOI":"10.5555\/3666122.3669630"},{"key":"22_CR21","doi-asserted-by":"publisher","unstructured":"West, M., Herman, G., Zilles, C.: PrairieLearn: mastery-based online problem solving with adaptive scoring and recommendations driven by machine learning. In: 2015 ASEE Annual Conference and Exposition Proceedings, pp. 26.1238.1\u201326.1238.14. ASEE Conferences, Seattle (2015). https:\/\/doi.org\/10.18260\/p.24575","DOI":"10.18260\/p.24575"},{"key":"22_CR22","unstructured":"West, M., Walters, N., Silva, M., Bretl, T., Zilles, C.: Integrating diverse learning tools using the PrairieLearn Platform. Virtual Event (2021). https:\/\/cssplice.org\/SIGCSE21\/proc\/SPLICE2021_SIGCSE_paper_10.pdf"},{"key":"22_CR23","doi-asserted-by":"publisher","unstructured":"Zhang, Q., Dong, J., Chen, H., Li, W., Huang, F., Huang, X.: Structure guided large language model for SQL generation (2024). https:\/\/doi.org\/10.48550\/arXiv.2402.13284. arXiv:2402.13284","DOI":"10.48550\/arXiv.2402.13284"},{"key":"22_CR24","doi-asserted-by":"publisher","unstructured":"Zhao, C., Silva, M., Poulsen, S.: Autograding mathematical induction proofs with natural language processing (2024). https:\/\/doi.org\/10.48550\/arXiv.2406.10268. arXiv:2406.10268","DOI":"10.48550\/arXiv.2406.10268"}],"container-title":["Communications in Computer and Information Science","Artificial Intelligence in Education. Posters and Late Breaking Results, Workshops and Tutorials, Industry and Innovation Tracks, Practitioners, Doctoral Consortium, Blue Sky, and WideAIED"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-99264-3_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T08:04:08Z","timestamp":1787817848000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-99264-3_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031992636","9783031992643"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-99264-3_22","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"21 July 2025","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":"Palermo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"22 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aied2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aied2025.itd.cnr.it\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}