{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T16:17:50Z","timestamp":1754151470239,"version":"3.41.2"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031984648","type":"print"},{"value":"9783031984655","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\/978-3-031-98465-5_6","type":"book-chapter","created":{"date-parts":[[2025,7,19]],"date-time":"2025-07-19T01:46:36Z","timestamp":1752889596000},"page":"44-51","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automated Scoring of Short Answer Questions with Large Language Models: Impacts of Model, Item, and Rubric Design"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5164-1014","authenticated-orcid":false,"given":"Scott","family":"Frohn","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9064-8876","authenticated-orcid":false,"given":"Tyler","family":"Burleigh","sequence":"additional","affiliation":[]},{"given":"Jing","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,20]]},"reference":[{"key":"6_CR1","unstructured":"Livingston, S.A.: Constructed-Response Test Questions: Why We Use Them; How We Score Them. R&D Connections. Number 11. Educational Testing Service (2009)"},{"key":"6_CR2","unstructured":"Landauer T.K., Laham D., Rehder B., Schreiner M.E.: How well can passage meaning be derived without using word order? a comparison of latent semantic analysis and humans. In: Proceedings of the 19th annual meeting of the Cognitive Science Society, pp. 412\u2013417 (1997)"},{"key":"6_CR3","doi-asserted-by":"publisher","unstructured":"Taghipour K., Ng H.T.: A neural approach to automated essay scoring. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 1882\u20131891 (2016) https:\/\/doi.org\/10.18653\/v1\/D16-1193","DOI":"10.18653\/v1\/D16-1193"},{"key":"6_CR4","unstructured":"Devlin J., Chang M.W., Lee K., Toutanova K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1, pp. 4171\u20134186 (2019)"},{"key":"6_CR5","doi-asserted-by":"publisher","unstructured":"Fife, J.H.: Scoring equations with automated scoring systems. ETS Res. Rep. Series 2017(1), 1\u201313 (2017). https:\/\/doi.org\/10.1002\/ets2.12170","DOI":"10.1002\/ets2.12170"},{"key":"6_CR6","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"8","key":"6_CR7","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)","journal-title":"OpenAI Blog"},{"key":"6_CR8","doi-asserted-by":"publisher","unstructured":"Morris W., Holmes L., Choi J.S., Crossley S.: Automated scoring of constructed response items in math assessment using large language models. Inter. J. Artifi. Intell. Educ., 1\u201328 (2024). https:\/\/doi.org\/10.1007\/s40593-024-00418-w","DOI":"10.1007\/s40593-024-00418-w"},{"key":"6_CR9","unstructured":"Kwako, A., Ormerod, C.: Improving transformer-based automated scoring of K-12 science items. In: Proceedings of the National Council on Measurement in Education (NCME) Conference, Philadelphia, PA. Cambium Assessment Inc (2024)"},{"key":"6_CR10","doi-asserted-by":"publisher","unstructured":"Henkel, O., Hills, L., Boxer, A., Roberts, B., Levonian, Z.: Can large language models make the grade? An empirical study evaluating LLMs\u2019 ability to mark short-answer questions in K-12 education. In: Proceedings of the Eleventh ACM Conference on Learning@ Scale, pp. 300\u2013304 (2024). https:\/\/doi.org\/10.1145\/3657604.3664693","DOI":"10.1145\/3657604.3664693"},{"key":"6_CR11","doi-asserted-by":"publisher","unstructured":"Pack A., Barrett A., Escalante J.: Large language models and automated essay scoring of English language learner writing: Insights into validity and reliability. Comput. Educ. Artifi. Intell. (6) (2024). https:\/\/doi.org\/10.1016\/j.caeai.2024.100234","DOI":"10.1016\/j.caeai.2024.100234"},{"key":"6_CR12","doi-asserted-by":"publisher","unstructured":"Lee G.G., Latif E., Wu X., Liu N., Zhai X.: Applying large language models and chain-of-thought for automatic scoring. Comput. Educ. Artifi. Intell. (6) (2024). https:\/\/doi.org\/10.1016\/j.caeai.2024.100213","DOI":"10.1016\/j.caeai.2024.100213"},{"key":"6_CR13","unstructured":"ETS: Responsible use of AI in assessment: ETS principles. ETS Research Institute Highlights (2024)"},{"key":"6_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-024-79208-2","volume":"1","author":"M Johnson","year":"2024","unstructured":"Johnson, M., Zhang, M.: Examining the responsible use of zero-shot AI approaches to scoring essays. Sci. Rep. 1, 1 (2024). https:\/\/doi.org\/10.1038\/s41598-024-79208-2","journal-title":"Sci. Rep."},{"key":"6_CR15","doi-asserted-by":"publisher","unstructured":"Landis J.R., Koch G.G.: An application of hierarchical kappa-type statistics in the assessment of majority agreement among multiple observers. Biometrics, 363\u2013374 (1977). https:\/\/doi.org\/10.2307\/2529786","DOI":"10.2307\/2529786"},{"key":"6_CR16","unstructured":"Casabianca, J.M., McCaffrey, D.F., Johnson, M.S., Alper, N., Zubenko, V.: Validity Arguments For Constructed Response Scoring Using Generative Artificial Intelligence Applications, arXiv preprint arXiv: 2501.02334\u00a0(2024)"}],"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\/978-3-031-98465-5_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,19]],"date-time":"2025-07-19T01:46:38Z","timestamp":1752889598000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-98465-5_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031984648","9783031984655"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-98465-5_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":"20 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"}}]}}