{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T13:45:36Z","timestamp":1782481536210,"version":"3.54.5"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032297433","type":"print"},{"value":"9783032297440","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T00:00:00Z","timestamp":1782518400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T00:00:00Z","timestamp":1782518400000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-29744-0_3","type":"book-chapter","created":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T12:45:05Z","timestamp":1782477905000},"page":"33-47","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Intelligent Tutoring Systems with\u00a0Instruction-Tuned LLMs: Automated Assessment of\u00a0Student Code Comprehension"],"prefix":"10.1007","author":[{"given":"Jeevan","family":"Chapagain","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vasile","family":"Rus","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,27]]},"reference":[{"key":"3_CR1","unstructured":"Achiam, J., et al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Banjade, R., Maharjan, N., Niraula, N.B., Gautam, D., Samei, B., Rus, V.: Evaluation dataset (dt-grade) and word weighting approach towards constructed short answers assessment in tutorial dialogue context. In: Proceedings of the 11th Workshop on Innovative use of NLP for Building Educational Applications, pp. 182\u2013187 (2016)","DOI":"10.18653\/v1\/W16-0520"},{"key":"3_CR3","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1007\/978-3-030-52240-7_8","volume-title":"Artificial Intelligence in Education","author":"L Camus","year":"2020","unstructured":"Camus, L., Filighera, A.: Investigating transformers for automatic short answer grading. In: Bittencourt, I.I., Cukurova, M., Muldner, K., Luckin, R., Mill\u00e1n, E. (eds.) AIED 2020. LNCS (LNAI), vol. 12164, pp. 43\u201348. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-52240-7_8"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Chapagain, J., Lekshmi, A.B., Akhuseyinoglu, K., Brusilovsky, P., Rus, V.: Selfcode 2.0: an annotated corpus of student and expert line-by-line explanations of code examples for automated assessment. In: The International FLAIRS Conference Proceedings, vol. 38, Florida Online Journals (2025)","DOI":"10.32473\/flairs.38.1.138727"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Chapagain, J., Rus, V.: Automated assessment of student self-explanation in code comprehension using pre-trained language models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 28996\u201329003 (2025)","DOI":"10.1609\/aaai.v39i28.35169"},{"key":"3_CR6","doi-asserted-by":"publisher","unstructured":"Chapagain, J., Sajib, M.I., Prodan, R., Rus, V.: A study of LLM generated line-by-line explanations in the context of conversational program comprehension tutoring systems. In: European Conference on Technology Enhanced Learning, pp. 64\u201374. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-72315-5_5","DOI":"10.1007\/978-3-031-72315-5_5"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Chapagain, J., Tamang, L., Banjade, R., Oli, P., Rus, V.: Automated assessment of student self-explanation during source code comprehension. In: The International FLAIRS Conference Proceedings, vol. 35 (2022)","DOI":"10.32473\/flairs.v35i.130540"},{"key":"3_CR8","unstructured":"Chen, M., et al.: Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 (2021)"},{"key":"3_CR9","first-page":"161","volume":"5","author":"MT Chi","year":"2000","unstructured":"Chi, M.T.: Self-explaining expository texts: the dual processes of generating inferences and repairing mental models. Adv. Inst. Psychol. 5, 161\u2013238 (2000)","journal-title":"Adv. Inst. Psychol."},{"key":"3_CR10","unstructured":"Dzikovska, M.O., Nielsen, R.D., Brew, C.: Towards effective tutorial feedback for explanation questions: a dataset and baselines. In: Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 200\u2013210. Association for Computational Linguistics (2012)"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Feng, Z., et\u00a0al.: Codebert: a pre-trained model for programming and natural languages. arXiv preprint arXiv:2002.08155 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Fowler, M., Chen, B., Azad, S., West, M., Zilles, C.: Autograding \u201cexplain in plain English\u201d questions using NLP. In: Proceedings of the 52nd ACM Technical Symposium on Computer Science Education, pp. 1163\u20131169 (2021)","DOI":"10.1145\/3408877.3432539"},{"key":"3_CR13","unstructured":"Gatto, J., Sharif, O., Seegmiller, P., Bohlman, P., Preum, S.M.: Text encoders lack knowledge: leveraging generative LLMs for domain-specific semantic textual similarity. arXiv preprint arXiv:2309.06541 (2023)"},{"key":"3_CR14","unstructured":"Google DeepMind: Codegemma: Open code models based on gemma. Technical report Google (2024). https:\/\/ai.google.dev\/gemma\/docs\/codegemma"},{"key":"3_CR15","unstructured":"Hicks, A., Akhuseyinoglu, K., Shaffer, C., Brusilovsky, P.: Live catalog of smart learning objects for computer science education. In: Sixth SPLICE Workshop (2020)"},{"issue":"2","key":"3_CR16","first-page":"3","volume":"1","author":"EJ Hu","year":"2022","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. ICLR 1(2), 3 (2022)","journal-title":"ICLR"},{"key":"3_CR17","unstructured":"Jiang, A.Q., et al.: Mistral 7b (2023). https:\/\/arxiv.org\/abs\/2310.06825"},{"key":"3_CR18","unstructured":"Jiang, A.Q., et\u00a0al.: Mistral 7b. Technical report, Mistral AI (2023). https:\/\/mistral.ai\/news\/announcing-mistral-7b\/"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Khayi, N.A., Rus, V., Tamang, L.: Towards improving open student answer assessment using pretrained transformers. In: The International FLAIRS Conference Proceedings, vol. 34 (2021)","DOI":"10.32473\/flairs.v34i1.128483"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Kumar, S., Chakrabarti, S., Roy, S.: Earth mover\u2019s distance pooling over siamese lstms for automatic short answer grading (2017)","DOI":"10.24963\/ijcai.2017\/284"},{"issue":"4","key":"3_CR21","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1023\/A:1025779619903","volume":"37","author":"C Leacock","year":"2003","unstructured":"Leacock, C., Chodorow, M.: C-rater: automated scoring of short-answer questions. Comput. Humanit. 37(4), 389\u2013405 (2003)","journal-title":"Comput. Humanit."},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Leinonen, J., et al.: Comparing code explanations created by students and large language models. arXiv preprint arXiv:2304.03938 (2023)","DOI":"10.1145\/3587102.3588785"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"McNeil, S., et al.: Experiences from using code explanations generated by large language models in a web software development e-book. In: Proceedings of the 54th ACM Technical Symposium on Computer Science Education, Toronto, Ontario, Canada, vol. 1, pp. 931\u2013937 (2023)","DOI":"10.1145\/3545945.3569785"},{"key":"3_CR24","unstructured":"Meta AI: Introducing meta llama 3: The most capable openly available LLM to date (2024). https:\/\/ai.meta.com\/blog\/meta-llama-3\/"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Minelli, R., Mocci, A., Lanza, M.: I know what you did last summer-an investigation of how developers spend their time. In: IEEE 23rd International Conference on Program Comprehension, pp. 25\u201335. IEEE (2015)","DOI":"10.1109\/ICPC.2015.12"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Mohler, M., Mihalcea, R.: Text-to-text semantic similarity for automatic short answer grading. In: Proceedings of the 12th Conference of the European Chapter of the ACL (EACL 2009), pp. 567\u2013575 (2009)","DOI":"10.3115\/1609067.1609130"},{"key":"3_CR27","unstructured":"Oli, P., Banjade, R., Chapagain, J., Rus, V.: Automated assessment of students\u2019 code comprehension using LLMs. arXiv preprint arXiv:2401.05399 (2023)"},{"key":"3_CR28","doi-asserted-by":"publisher","first-page":"27730","DOI":"10.52202\/068431-2011","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR29","doi-asserted-by":"publisher","first-page":"53728","DOI":"10.52202\/075280-2338","volume":"36","author":"R Rafailov","year":"2023","unstructured":"Rafailov, R., Sharma, A., Mitchell, E., Manning, C.D., Ermon, S., Finn, C.: Direct preference optimization: your language model is secretly a reward model. Adv. Neural. Inf. Process. Syst. 36, 53728\u201353741 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"1","key":"3_CR30","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1007\/s40593-015-0070-z","volume":"27","author":"K Rivers","year":"2017","unstructured":"Rivers, K., Koedinger, K.R.: Data-driven hint generation in vast solution spaces: a self-improving python programming tutor. Int. J. Artif. Intell. Educ. 27(1), 37\u201364 (2017)","journal-title":"Int. J. Artif. Intell. Educ."},{"key":"3_CR31","unstructured":"Rozi\u00e8re, B., et al.: Code llama: open foundation models for code. arXiv preprint arXiv:2308.12950 (2023)"},{"issue":"1","key":"3_CR32","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1023\/A:1018976708691","volume":"9","author":"S Rugaber","year":"2000","unstructured":"Rugaber, S.: The use of domain knowledge in program understanding. Ann. Softw. Eng. 9(1), 143\u2013192 (2000)","journal-title":"Ann. Softw. Eng."},{"key":"3_CR33","unstructured":"Rus, V., Akhuseyinoglu, K., Chapagain, J., Tamang, L., Brusilovsky, P.: Prompting for free self-explanations promotes better code comprehension. In: 5th Educational Data Mining in CS Education Workshop at EDM2021 (2021)"},{"key":"3_CR34","unstructured":"Sanh, V., et al.: Multitask prompted training enables zero-shot task generalization. arXiv preprint arXiv:2110.08207 (2021)"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Sultan, M.A., Salazar, C., Sumner, T.: Fast and easy short answer grading with high accuracy. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1070\u20131075 (2016)","DOI":"10.18653\/v1\/N16-1123"},{"key":"3_CR36","unstructured":"Touvron, H., et al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"3_CR37","unstructured":"Wang, Y., et al.: Self-instruct: aligning language models with self-generated instructions. arXiv preprint arXiv:2212.10560 (2022)"},{"key":"3_CR38","unstructured":"Wei, J., et al.: Finetuned language models are zero-shot learners. arXiv preprint arXiv:2109.01652 (2021)"},{"issue":"10","key":"3_CR39","doi-asserted-by":"publisher","first-page":"951","DOI":"10.1109\/TSE.2017.2734091","volume":"44","author":"X Xia","year":"2017","unstructured":"Xia, X., Bao, L., Lo, D., Xing, Z., Hassan, A.E., Li, S.: Measuring program comprehension: a large-scale field study with professionals. IEEE Trans. Softw. Eng. 44(10), 951\u2013976 (2017)","journal-title":"IEEE Trans. Softw. Eng."},{"key":"3_CR40","unstructured":"Zhong, Q., Ding, L., Liu, J., Du, B., Tao, D.: Can chatgpt understand too? A comparative study on chatgpt and fine-tuned bert. arXiv preprint arXiv:2302.10198 (2023)"}],"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\/978-3-032-29744-0_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T12:45:45Z","timestamp":1782477945000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-29744-0_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,27]]},"ISBN":["9783032297433","9783032297440"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-29744-0_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,27]]},"assertion":[{"value":"27 June 2026","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":"Seoul","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","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 June 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aied2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.aied-conference.org\/2026","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}