{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T13:46:15Z","timestamp":1782481575760,"version":"3.54.5"},"publisher-location":"Cham","reference-count":39,"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_36","type":"book-chapter","created":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T12:49:46Z","timestamp":1782478186000},"page":"539-554","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SciEval: A Benchmark for\u00a0Automatic Evaluation of\u00a0K\u201312 Science Instructional Materials"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0537-3546","authenticated-orcid":false,"given":"Zhaohui","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2877-0117","authenticated-orcid":false,"given":"Peng","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0916-0595","authenticated-orcid":false,"given":"Zhiyuan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0897-5850","authenticated-orcid":false,"given":"Honglu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5962-1277","authenticated-orcid":false,"given":"Zeyuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5692-2042","authenticated-orcid":false,"given":"Tingting","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2620-4859","authenticated-orcid":false,"given":"Jinjun","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,27]]},"reference":[{"key":"36_CR1","doi-asserted-by":"publisher","unstructured":"Abdul\u00a0Wahid, R., Nadim, M.S.N., Sulaiman, S., Shaharudin, S.A., Jupikil, M.D., Su, I.J.S.A.: Automated generation of curriculum-aligned multiple-choice questions for Malaysian secondary mathematics using generative AI (2025). https:\/\/doi.org\/10.48550\/arXiv.2508.04442. https:\/\/arxiv.org\/abs\/2508.04442","DOI":"10.48550\/arXiv.2508.04442"},{"key":"36_CR2","unstructured":"Achieve, Inc.: Equip rubric for lessons & units: Science (version 3.0) (2016). https:\/\/www.nextgenscience.org\/resources\/equip-rubric-lessons-units-science"},{"key":"36_CR3","unstructured":"Biological Sciences Curriculum Study (BSCS): Field-test version: BSCS science learning NGSS-aligned instructional materials (2019). https:\/\/bscs.org\/bscs-science-learning\/. Accessed Aug 2025"},{"key":"36_CR4","unstructured":"Camilli, G.: An NLP crosswalk between the common core state standards and NAEP item specifications. arXiv preprint arXiv:2405.17284 (2024)"},{"key":"36_CR5","unstructured":"Carnegie Corporation of New York: Instructional materials matter (2017). https:\/\/www.carnegie.org\/news\/articles\/instructional-materials-matter\/"},{"key":"36_CR6","unstructured":"Clark, H.B., Margetts, M., Beaven, T., Braverman, B., Biggart, A.M.: Auto-evaluation: a critical measure in driving improvements in quality and safety of AI-generated lesson resources (2025)"},{"issue":"1","key":"36_CR7","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1177\/001316446002000104","volume":"20","author":"J Cohen","year":"1960","unstructured":"Cohen, J.: A coefficient of agreement for nominal scales. Educ. Psychol. Measur. 20(1), 37\u201346 (1960)","journal-title":"Educ. Psychol. Measur."},{"key":"36_CR8","unstructured":"Comanici, G., et al.: Gemini 2.5: pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arXiv preprint arXiv:2507.06261 (2025)"},{"key":"36_CR9","doi-asserted-by":"publisher","first-page":"10088","DOI":"10.52202\/075280-0441","volume":"36","author":"T Dettmers","year":"2023","unstructured":"Dettmers, T., Pagnoni, A., Holtzman, A., Zettlemoyer, L.: QLORA: efficient finetuning of quantized LLMs. Adv. Neural. Inf. Process. Syst. 36, 10088\u201310115 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"36_CR10","unstructured":"Dubey, A., et al.: The llama 3 herd of models. arXiv e-prints pp. arXiv-2407 (2024)"},{"key":"36_CR11","unstructured":"Fu, Y., et al.: Text-based approaches to item alignment to content standards in large-scale reading & writing tests. In: Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers, pp. 19\u201336 (2025)"},{"key":"36_CR12","doi-asserted-by":"crossref","unstructured":"Hauk, D., Soujon, N.: How reliable are large language models in analyzing the quality of written lesson plans? A mixed-methods study from a teacher internship program. Comput. Educ. Artif. Intell. 100538 (2025)","DOI":"10.1016\/j.caeai.2025.100538"},{"key":"36_CR13","unstructured":"He, P., Li, Z., Wang, Z., Xiong, J., Li, T.: Judging the Judges: Human Validation of Multi-LLM Evaluation for High-Quality K\u201312 Science Instructional Materials. arXiv preprint arXiv:2602.13243 (2026)"},{"key":"36_CR14","unstructured":"Hendrycks, D., et al.: Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300 (2020)"},{"key":"36_CR15","unstructured":"Hendrycks, D., et al.: Measuring mathematical problem solving with the math dataset. arXiv preprint arXiv:2103.03874 (2021)"},{"issue":"2","key":"36_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":"36_CR17","unstructured":"Hurst, A., et al.: GPT-4o system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"36_CR18","unstructured":"Inc., A.: Equip rubric for lessons and units: science (2016). https:\/\/www.nextgenscience.org\/resources\/equip-rubric-lessons-units-science"},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"Lee, G.G., Zhai, X.: Using chatgpt for science learning: a study on pre-service teachers\u2019 lesson planning. IEEE Trans. Learn. Technol. 17 (2024)","DOI":"10.1109\/TLT.2024.3401457"},{"key":"36_CR20","unstructured":"Li, H., Xu, T., Tang, J., Wen, Q.: Automate knowledge concept tagging on math questions with LLMs. arXiv preprint arXiv:2403.17281 (2024)"},{"key":"36_CR21","doi-asserted-by":"crossref","unstructured":"Li, Z., Tomar, Y., Passonneau, R.J.: A semantic feature-wise transformation relation network for automatic short answer grading. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, p.\u00a06030 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.487"},{"key":"36_CR22","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1162\/tacl_a_00638","volume":"12","author":"NF Liu","year":"2024","unstructured":"Liu, N.F., et al.: Lost in the middle: how language models use long contexts. Trans. Assoc. Comput. Linguist. 12, 157\u2013173 (2024)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"36_CR23","unstructured":"National Academies of Sciences, Engineering, and Medicine: Design, Selection, and Implementation of Instructional Materials for the Next Generation Science Standards. The National Academies Press, Washington, DC (2018)"},{"key":"36_CR24","unstructured":"National Research Council: A Framework for K\u201312 Science Education: Practices, Crosscutting Concepts, and Core Ideas. National Academies Press, Washington, DC (2012). https:\/\/doi.org\/10.17226\/13165"},{"key":"36_CR25","unstructured":"NextGenScience: toward NGSS design: EQuIP rubric for science detailed guidance (2021). https:\/\/ngs.wested.org"},{"key":"36_CR26","unstructured":"NGSS Lead States: Next generation science standards: For states, by states. The National Academies Press, Washington, DC (2013)"},{"issue":"8","key":"36_CR27","doi-asserted-by":"publisher","first-page":"911","DOI":"10.1080\/1046560X.2021.1902631","volume":"32","author":"J Nordine","year":"2021","unstructured":"Nordine, J., et al.: Promoting coherent science instruction through coherent science teacher education: a model framework for program design. J. Sci. Teacher Educ. 32(8), 911\u2013933 (2021)","journal-title":"J. Sci. Teacher Educ."},{"key":"36_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":"36_CR29","doi-asserted-by":"crossref","unstructured":"Ouyang, Y., Quan, J., Wang, H., Zeng, Y., Chen, L.: Lang: a lesson plan generation framework via multi-form interaction with large language models (2025)","DOI":"10.21203\/rs.3.rs-6808103\/v1"},{"issue":"4","key":"36_CR30","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1002\/sce.21248","volume":"101","author":"WR Penuel","year":"2017","unstructured":"Penuel, W.R.: Research-practice partnerships as a strategy for promoting equitable science teaching and learning through leveraging everyday science. Sci. Educ. 101(4), 520\u2013525 (2017). https:\/\/doi.org\/10.1002\/sce.21248","journal-title":"Sci. Educ."},{"key":"36_CR31","doi-asserted-by":"crossref","unstructured":"Singh, R., Mangat, N.S.: Stratified sampling. In: Elements of Survey Sampling, pp. 102\u2013144. Springer (1996)","DOI":"10.1007\/978-94-017-1404-4_5"},{"issue":"3","key":"36_CR32","first-page":"1","volume":"17","author":"K Tan","year":"2025","unstructured":"Tan, K., Yao, J., Pang, T., Fan, C., Song, Y.: ELF: educational LLM framework of improving and evaluating AI-generated content for classroom teaching. ACM J. Data Inf. Q. 17(3), 1\u201323 (2025)","journal-title":"ACM J. Data Inf. Q."},{"key":"36_CR33","doi-asserted-by":"publisher","first-page":"24824","DOI":"10.52202\/068431-1800","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. Adv. Neural. Inf. Process. Syst. 35, 24824\u201324837 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"36_CR34","unstructured":"Yang, A., et al.: Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)"},{"key":"36_CR35","doi-asserted-by":"crossref","unstructured":"Ye, F., Cui, H., Ke, C., Zhong, W., Zhang, S., Zhang, L.: An automatic model for lesson plans generation based on logical chains and prompt tuning. In: International Symposium on Emerging Technologies for Education, pp. 250\u2013264. Springer (2024)","DOI":"10.1007\/978-981-96-4407-0_21"},{"key":"36_CR36","doi-asserted-by":"publisher","unstructured":"Yuan, B., Hu, J.: An exploration of higher education course evaluation by large language models (2024). https:\/\/doi.org\/10.48550\/arXiv.2411.02455. https:\/\/arxiv.org\/abs\/2411.02455","DOI":"10.48550\/arXiv.2411.02455"},{"issue":"1","key":"36_CR37","doi-asserted-by":"publisher","first-page":"1784","DOI":"10.1057\/s41599-025-06004-2","volume":"12","author":"Y Zheng","year":"2025","unstructured":"Zheng, Y., Huang, S., Zeng, X., Huang, Y., Liu, Z., Luo, W.: Knowledge-enhanced large language models for automatic lesson plan generation. Humanit. Soc. Sci. Commun. 12(1), 1784 (2025)","journal-title":"Humanit. Soc. Sci. Commun."},{"key":"36_CR38","doi-asserted-by":"crossref","unstructured":"Zheng, Y., et al.: Automatic lesson plan generation via large language models with self-critique prompting. In: International Conference on Artificial Intelligence in Education, pp. 163\u2013178. Springer (2024)","DOI":"10.1007\/978-3-031-64315-6_13"},{"key":"36_CR39","unstructured":"He, P., Li, Z., Wang, Z., Xiong, J., Li, T.: Judging the judges: human validation of multi-LLM evaluation for high-quality K\u201312 science instructional materials. arXiv preprint arXiv:2602.13243 (2026)"}],"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_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T12:50:31Z","timestamp":1782478231000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-29744-0_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,27]]},"ISBN":["9783032297433","9783032297440"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-29744-0_36","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"}}]}}