{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T23:35:32Z","timestamp":1771457732178,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":37,"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_28","type":"book-chapter","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T10:06:23Z","timestamp":1753351583000},"page":"328-341","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["IterSelectTune: An Iterative Data Selection Framework for Efficient Instruction Tuning"],"prefix":"10.1007","author":[{"given":"Jielin","family":"Song","sequence":"first","affiliation":[]},{"given":"Siyu","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Bin","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Yanghui","family":"Rao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,25]]},"reference":[{"key":"28_CR1","unstructured":"Touvron, H., et al.: Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"28_CR2","unstructured":"Workshop, B., et al.: Bloom: A 176b-parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100 (2022)"},{"key":"28_CR3","unstructured":"Longpre, S., et al.: The flan collection: Designing data and methods for effective instruction tuning. In: ICML, pp. 22631\u201322648 (2023)"},{"key":"28_CR4","unstructured":"Chen, L., Chen, J., Goldstein, T., Huang, H., Zhou, T.: Instructzero: Efficient instruction optimization for black-box large language models. In: ICML (2024)"},{"key":"28_CR5","unstructured":"Wei, J., et al.: Finetuned language models are zero-shot learners. In: ICLR (2022)"},{"key":"28_CR6","unstructured":"Zhou, C., et al.: LIMA: less is more for alignment. In: NeurIPS (2023)"},{"key":"28_CR7","unstructured":"Cao, Y., Kang, Y., Sun, L.: Instruction mining: High-quality instruction data selection for large language models. arXiv preprint arXiv:2307.06290 (2023)"},{"key":"28_CR8","unstructured":"Lu, K., et al.: #instag: Instruction tagging for analyzing supervised fine-tuning of large language models. In: ICLR (2024)"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: One-shot learning as instruction data prospector for large language models. In: ACL, pp. 4586\u20134601 (2024)","DOI":"10.18653\/v1\/2024.acl-long.252"},{"key":"28_CR10","unstructured":"Wu, S., et al.: Self-evolved diverse data sampling for efficient instruction tuning. arXiv preprint arXiv:2311.08182 (2023)"},{"key":"28_CR11","unstructured":"Chen, L., et al.: Alpagasus: Training a better alpaca with fewer data. In: ICLR (2024)"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: From quantity to quality: Boosting LLM performance with self-guided data selection for instruction tuning. In: NAACL-HLT, pp. 7602\u20137635 (2024)","DOI":"10.18653\/v1\/2024.naacl-long.421"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: G-eval: NLG evaluation using gpt-4 with better human alignment. In: EMNLP, pp. 2511\u20132522 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.153"},{"key":"28_CR14","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT, pp. 4171\u20134186 (2019)"},{"issue":"3","key":"28_CR15","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1109\/3477.764879","volume":"29","author":"K Kummamuru","year":"1999","unstructured":"Kummamuru, K., Murty, M.N.: Genetic k-means algorithm. IEEE Trans. Syst. Man Cybern. Part B 29(3), 433\u2013439 (1999)","journal-title":"IEEE Trans. Syst. Man Cybern. Part B"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-bert: Sentence embeddings using siamese bert-networks. In: EMNLP-IJCNLP, pp. 3980\u20133990 (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"28_CR17","unstructured":"OpenAI: GPT-4 technical report. CoRR abs\/2303.08774 (2023)"},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Ko, M., Lee, J., Kim, H., Kim, G., Kang, J.: Look at the first sentence: Position bias in question answering. In: EMNLP, pp. 1109\u20131121 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.84"},{"issue":"6","key":"28_CR19","first-page":"7","volume":"3","author":"R Taori","year":"2023","unstructured":"Taori, R., et al.: Alpaca: A strong, replicable instruction-following model. Stanford Center for Research on Foundation Models. 3(6), 7 (2023)","journal-title":"Stanford Center for Research on Foundation Models."},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Yin, D., et al.: Dynosaur: A dynamic growth paradigm for instruction-tuning data curation. In: EMNLP, pp. 4031\u20134047 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.245"},{"key":"28_CR21","unstructured":"Luo, Z., et al.: Wizardcoder: Empowering code large language models with evol-instruct. In: ICLR (2024)"},{"key":"28_CR22","doi-asserted-by":"crossref","unstructured":"Wu, M., et al.: Lamini-lm: A diverse herd of distilled models from large-scale instructions. In: EACL, pp. 944\u2013964 (2024)","DOI":"10.18653\/v1\/2024.eacl-long.57"},{"key":"28_CR23","unstructured":"Conover, M., et al.: Free dolly: Introducing the world\u2019s first truly open instruction-tuned llm. Company Blog of Databricks (2023)"},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Honovich, O., Scialom, T., Levy, O., Schick, T.: Unnatural instructions: Tuning language models with (almost) no human labor. In: ACL, pp. 14409\u201314428 (2023)","DOI":"10.18653\/v1\/2023.acl-long.806"},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"K\u00f6ksal, A., Schick, T., Korhonen, A., Sch\u00fctze, H.: Longform: Effective instruction tuning with reverse instructions. In: Findings of the EMNLP, pp. 7056\u20137078 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.414"},{"key":"28_CR26","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Self-instruct: Aligning language models with self-generated instructions. In: ACL, pp. 13484\u201313508 (2023)","DOI":"10.18653\/v1\/2023.acl-long.754"},{"key":"28_CR27","unstructured":"Chiang, W.L., et al.: Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality (2023). https:\/\/lmsys.org\/blog\/2023-03-30-vicuna\/"},{"key":"28_CR28","unstructured":"Xu, C., et al.: Wizardlm: Empowering large pre-trained language models to follow complex instructions. In: ICLR (2024)"},{"key":"28_CR29","unstructured":"Geng, X., et al.: Koala: A dialogue model for academic research. Blog post, April 1, 6 (2023)"},{"key":"28_CR30","doi-asserted-by":"crossref","unstructured":"Chang, Y., 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":"28_CR31","doi-asserted-by":"crossref","unstructured":"Zellers, R., Holtzman, A., Bisk, Y., Farhadi, A., Choi, Y.: Hellaswag: Can a machine really finish your sentence? In: ACL, pp. 4791\u20134800 (2019)","DOI":"10.18653\/v1\/P19-1472"},{"key":"28_CR32","unstructured":"Clark, P., et al.: Think you have solved question answering? try arc, the ai2 reasoning challenge. arXiv preprint arXiv:1803.05457 (2018)"},{"key":"28_CR33","doi-asserted-by":"crossref","unstructured":"Lin, S., Hilton, J., Evans, O.: Truthfulqa: Measuring how models mimic human falsehoods. In: ACL, pp. 3214\u20133252 (2022)","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"28_CR34","unstructured":"Hendrycks, D., et al.: Measuring massive multitask language understanding. In: ICLR (2021)"},{"key":"28_CR35","doi-asserted-by":"crossref","unstructured":"Poliak, A.: A survey on recognizing textual entailment as an NLP evaluation. In: Eval4NLP, pp. 92\u2013109 (2020)","DOI":"10.18653\/v1\/2020.eval4nlp-1.10"},{"key":"28_CR36","doi-asserted-by":"crossref","unstructured":"Suzgun, M., et al.: Challenging big-bench tasks and whether chain-of-thought can solve them. In: ACL, pp. 13003\u201313051 (2023)","DOI":"10.18653\/v1\/2023.findings-acl.824"},{"key":"28_CR37","unstructured":"Dua, D., et al.: DROP: A reading comprehension benchmark requiring discrete reasoning over paragraphs. In: NAACL-HLT, pp. 2368\u20132378 (2019)"}],"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_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T21:40:37Z","timestamp":1757281237000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-0014-7_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819500130","9789819500147"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-0014-7_28","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"}}]}}