{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T10:19:56Z","timestamp":1780913996849,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819500130","type":"print"},{"value":"9789819500147","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\/978-981-95-0014-7_31","type":"book-chapter","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T10:05:55Z","timestamp":1753351555000},"page":"366-377","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automated Construction of High-quality Evaluation Datasets Based on LLMs"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9342-0498","authenticated-orcid":false,"given":"Liming","family":"Kang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rongduo","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meiping","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhixiang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nan","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haining","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,25]]},"reference":[{"key":"31_CR1","unstructured":"Moradi, M., Yan, K., Colwell, D., et al.: Exploring the landscape of large language models: foundations, techniques, and challenges (2024)"},{"key":"31_CR2","doi-asserted-by":"publisher","first-page":"26839","DOI":"10.1109\/ACCESS.2024.3365742","volume":"12","author":"MAK Raiaan","year":"2024","unstructured":"Raiaan, M.A.K., Mukta, M.S.H., Fatema, K., et al.: A review on large language models: architectures, applications, taxonomies, open issues and challenges. IEEE Access 12, 26839\u201326874 (2024)","journal-title":"IEEE Access"},{"key":"31_CR3","unstructured":"Guo, Z., Jin, R., Liu, C., et al.: Evaluating large language models: a comprehensive survey (2023)"},{"key":"31_CR4","unstructured":"Xu, C., Guan, S., Greene, D., Kechadi, M.-T.: Benchmark data contamination of large language models: a survey (2024)"},{"key":"31_CR5","unstructured":"OpenAI. GPT-4 technical report. OpenAI, Tech. Rep. (2023)"},{"key":"31_CR6","unstructured":"OpenAI. Achiam, J., Adler, S., et al.: GPT-4 technical report (2024)"},{"key":"31_CR7","unstructured":"Zhang, B., Takeuchi, M., Kawahara, R., et al.: Enterprise benchmarks for large language model evaluation (2024)"},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"Laskar, M.T.R., Alqahtani, S., Bari, M.S., et al.: A systematic survey and critical review on evaluating large language models: challenges, limitations, and recommendations. In: Proc. Conf. Empirical Methods Natural Language Process. pp. 13785\u201313816 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.764"},{"key":"31_CR9","doi-asserted-by":"crossref","unstructured":"Chang, Y., Wang, X., Wang, J., et al.: A survey on evaluation of large language models. ACM Trans. Intell. Syst. Technol. 15(3), 39:1\u201339:45 (2024)","DOI":"10.1145\/3641289"},{"key":"31_CR10","doi-asserted-by":"crossref","unstructured":"Wu, Z.,R. L. L. IV, Walsh, P., et al.: Continued pretraining for better zero- and few-shot promptability (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.300"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Bezirhan, U., von Davier, M.: Automated reading passage generation with OpenAI\u2019s large language model. Comput. Educ.: Artif. Intell. 5, 100161 (2023)","DOI":"10.1016\/j.caeai.2023.100161"},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Joshi, A., Srinivas, C., Firat, E.E., Laramee, R.S.: Evaluating the recommendations of LLMs to teach a visualization technique using bloom\u2019s taxonomy. Electron. Imaging 36(1), 360\u20131\u2013360\u20131 (2024)","DOI":"10.2352\/EI.2024.36.1.VDA-360"},{"key":"31_CR13","doi-asserted-by":"crossref","unstructured":"Svens\u00a8ater, G., Rohlin, M.: Assessment model blending formative and summative assessments using the SOLO taxonomy. Eur. J. Dent. Educ. 27(1), 149\u2013157 (2023)","DOI":"10.1111\/eje.12787"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Scaria, N., Chenna, S.D., Subramani, D.: Automated educational question generation at different Bloom\u2019s skill levels using large lan guage models: Strategies and evaluation. In: Artificial Intelligence in Education. Springer, pp. 165\u2013179 (2024)","DOI":"10.1007\/978-3-031-64299-9_12"},{"issue":"2","key":"31_CR15","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1080\/0729436950140201","volume":"14","author":"GM Boulton-Lewis","year":"1995","unstructured":"Boulton-Lewis, G.M.: The SOLO taxonomy as a means of shaping and assessing learning in higher education. Higher Educ. Res. Dev. 14(2), 143\u2013154 (1995)","journal-title":"Higher Educ. Res. Dev."},{"issue":"2","key":"31_CR16","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1021\/acs.jchemed.0c00183","volume":"98","author":"J Barbera","year":"2021","unstructured":"Barbera, J., Naibert, N., Komperda, R., Pentecost, T.C.: Clarity on cronbach\u2019s alpha use. J. Chem. Educ. 98(2), 257\u2013258 (2021)","journal-title":"J. Chem. Educ."},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Business Management Studies: Int. J. 8(3), 2694\u20132726 (2020). https:\/\/www.bmij.org\/index.php\/1\/article\/view\/1540","DOI":"10.15295\/bmij.v8i3.1540"},{"key":"31_CR18","unstructured":"Cobbe, K., Kosaraju, V., Bavarian, M., et al.: Training verifiers to solve math word problems (2021)"},{"key":"31_CR19","unstructured":"Li, D., Murr, L.: HumanEval on latest GPT models\u2013 2024 (2024)"},{"key":"31_CR20","unstructured":"Yatskar, M.: A qualitative comparison of CoQA, SQuAD 2.0 and QuAC (2019)"},{"issue":"5","key":"31_CR21","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1109\/MIS.2024.3441136","volume":"39","author":"DE O\u2019Leary","year":"2024","unstructured":"O\u2019Leary, D.E.: Do ChatGPT 4o, 4, and 3.5 generate \u201csimilar\u201d ratings? findings and implications. IEEE Intell. Syst. 39(5), 78\u201381 (2024)","journal-title":"IEEE Intell. Syst."},{"key":"31_CR22","unstructured":"DeepSeek-AI, Liu, A., Feng, B., et al.: DeepSeek-V3 technical report (2024)"},{"key":"31_CR23","unstructured":"Qwen, Yang, A., Yang, B., et al.: Qwen2.5 technical report (2025)"},{"key":"31_CR24","unstructured":"Team GLM, Zeng, A., Xu, B., et al.: ChatGLM: A family of large language models from GLM-130B to GLM-4 (2024)"},{"key":"31_CR25","unstructured":"AI, Young, A., Chen, B., et al.: Yi: Open foundation models by 01.AI (2024)"},{"key":"31_CR26","unstructured":"Gemma Team, Mesnard, T., Hardin, C., et al.: Gemma: open models based on gemini research and technology (2024)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-0014-7_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T09:54:52Z","timestamp":1780912492000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-0014-7_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819500130","9789819500147"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-0014-7_31","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":"25 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}