{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T11:59:39Z","timestamp":1742990379106,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819611508"},{"type":"electronic","value":"9789819611515"}],"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\/978-981-96-1151-5_6","type":"book-chapter","created":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T16:00:53Z","timestamp":1738857653000},"page":"51-60","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CollectiveSFT: Scaling Large Language Models for\u00a0Chinese Medical Benchmark with\u00a0Collective Instructions in\u00a0Healthcare"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1597-6042","authenticated-orcid":false,"given":"Jingwei","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8287-0453","authenticated-orcid":false,"given":"Minghuan","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7345-5071","authenticated-orcid":false,"given":"Min","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5386-0277","authenticated-orcid":false,"given":"Ruixue","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2189-9153","authenticated-orcid":false,"given":"Hamid","family":"Alinejad-Rokny","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,7]]},"reference":[{"key":"6_CR1","unstructured":"Chinese medical dialogue data \n\n                  \n                \n (2019). https:\/\/github.com\/Toyhom\/Chinese-medical-dialogue-data"},{"key":"6_CR2","unstructured":"01.AI:: Yi: Open foundation models by 01.AI (2024)"},{"key":"6_CR3","unstructured":"Baichuan: Baichuan 2: open large-scale language models. arXiv preprint arXiv:2309.10305 (2023). https:\/\/arxiv.org\/abs\/2309.10305"},{"key":"6_CR4","unstructured":"Bao, Z., et al.: DISC-MedLLM: bridging general large language models and real-world medical consultation (2023)"},{"key":"6_CR5","unstructured":"Chen, J., et al.: HuatuoGPT-II, one-stage training for medical adaption of LLMs (2023). https:\/\/arxiv.org\/abs\/2311.09774"},{"issue":"3","key":"6_CR6","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1186\/s12911-020-1122-3","volume":"20","author":"N Chen","year":"2020","unstructured":"Chen, N., Su, X., Liu, T., Hao, Q., Wei, M.: A benchmark dataset and case study for Chinese medical question intent classification. BMC Med. Inform. Decis. Mak. 20(3), 125 (2020). https:\/\/doi.org\/10.1186\/s12911-020-1122-3","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"6_CR7","unstructured":"Du, Y., et al.: The calla dataset: probing LLMs\u2019 interactive knowledge acquisition from Chinese medical literature (2023)"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Du, Z., et al.: GLM: general language model pretraining with autoregressive blank infilling (2022). https:\/\/arxiv.org\/abs\/2103.10360","DOI":"10.18653\/v1\/2022.acl-long.26"},{"issue":"2","key":"6_CR9","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1186\/s12911-019-0761-8","volume":"19","author":"J He","year":"2019","unstructured":"He, J., Fu, M., Tu, M.: Applying deep matching networks to Chinese medical question answering: a study and a dataset. BMC Med. Inform. Decis. Mak. 19(2), 52 (2019). https:\/\/doi.org\/10.1186\/s12911-019-0761-8","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"6_CR10","unstructured":"He, X., et al.: MedDialog: two large-scale medical dialogue datasets (2020)"},{"key":"6_CR11","doi-asserted-by":"publisher","unstructured":"Honovich, O., Scialom, T., Levy, O., Schick, T.: Unnatural instructions: tuning language models with (almost) no human labor. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 14409\u201314428. Association for Computational Linguistics, Toronto (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.806, https:\/\/aclanthology.org\/2023.acl-long.806","DOI":"10.18653\/v1\/2023.acl-long.806"},{"key":"6_CR12","unstructured":"InternLM:: InternLM2 technical report (2024)"},{"key":"6_CR13","doi-asserted-by":"publisher","unstructured":"Jin, Q., Dhingra, B., Liu, Z., Cohen, W., Lu, X.: PubMedQA: a dataset for biomedical research question answering. In: Inui, K., Jiang, J., Ng, V., Wan, X. (eds.) Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 2567\u20132577. Association for Computational Linguistics, Hong Kong (2019). https:\/\/doi.org\/10.18653\/v1\/D19-1259, https:\/\/aclanthology.org\/D19-1259","DOI":"10.18653\/v1\/D19-1259"},{"key":"6_CR14","doi-asserted-by":"publisher","unstructured":"Labrak, Y., et al.: FrenchMedMCQA: a French multiple-choice question answering dataset for medical domain. In: Lavelli, A., Holderness, E., Jimeno\u00a0Yepes, A., Minard, A.L., Pustejovsky, J., Rinaldi, F. (eds.) Proceedings of the 13th International Workshop on Health Text Mining and Information Analysis (LOUHI), pp. 41\u201346. Association for Computational Linguistics, Abu Dhabi (2022). https:\/\/doi.org\/10.18653\/v1\/2022.louhi-1.5, https:\/\/aclanthology.org\/2022.louhi-1.5","DOI":"10.18653\/v1\/2022.louhi-1.5"},{"key":"6_CR15","doi-asserted-by":"publisher","unstructured":"Li, D., Hu, B., Chen, Q., Peng, W., Wang, A.: Towards medical machine reading comprehension with structural knowledge and plain text. In: Webber, B., Cohn, T., He, Y., Liu, Y. (eds.) Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1427\u20131438. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.111, https:\/\/aclanthology.org\/2020.emnlp-main.111","DOI":"10.18653\/v1\/2020.emnlp-main.111"},{"key":"6_CR16","doi-asserted-by":"publisher","unstructured":"Li, J., Zhong, S., Chen, K.: MLEC-QA: a Chinese multi-choice biomedical question answering dataset. In: Moens, M.F., Huang, X., Specia, L., Yih, S.W.T. (eds.) Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 8862\u20138874. Association for Computational Linguistics, Online and Punta Cana (2021). https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.698, https:\/\/aclanthology.org\/2021.emnlp-main.698","DOI":"10.18653\/v1\/2021.emnlp-main.698"},{"key":"6_CR17","unstructured":"Li, Q., et al.: From beginner to expert: modeling medical knowledge into general LLMs (2024). https:\/\/arxiv.org\/abs\/2312.01040"},{"key":"6_CR18","doi-asserted-by":"publisher","unstructured":"Mishra, S., Khashabi, D., Baral, C., Hajishirzi, H.: Cross-task generalization via natural language crowdsourcing instructions. In: Muresan, S., Nakov, P., Villavicencio, A. (eds.) Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 3470\u20133487. Association for Computational Linguistics, Dublin (2022). https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.244, https:\/\/aclanthology.org\/2022.acl-long.244","DOI":"10.18653\/v1\/2022.acl-long.244"},{"key":"6_CR19","unstructured":"OpenAI:: GPT-4 Technical report (2023)"},{"key":"6_CR20","unstructured":"Pal, A., Umapathi, L.K., Sankarasubbu, M.: MedMCQA: a large-scale multi-subject multi-choice dataset for medical domain question answering. In: Flores, G., Chen, G.H., Pollard, T., Ho, J.C., Naumann, T. (eds.) Proceedings of the Conference on Health, Inference, and Learning. Proceedings of Machine Learning Research, vol.\u00a0174, pp. 248\u2013260. PMLR (2022). https:\/\/proceedings.mlr.press\/v174\/pal22a.html"},{"key":"6_CR21","unstructured":"QwenLM:: Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)"},{"key":"6_CR22","unstructured":"Taori, R., Gulrajani, I., Zhang, T., Dubois, Y., Li, X., Guestrin, C., Liang, P., Hashimoto, T.B.: Stanford alpaca: an instruction-following llama model (2023). https:\/\/github.com\/tatsu-lab\/stanford_alpaca"},{"key":"6_CR23","doi-asserted-by":"publisher","unstructured":"Vilares, D., G\u00f3mez-Rodr\u00edguez, C.: HEAD-QA: a healthcare dataset for complex reasoning. In: Korhonen, A., Traum, D., M\u00e0rquez, L. (eds.) Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 960\u2013966. Association for Computational Linguistics, Florence (2019). https:\/\/doi.org\/10.18653\/v1\/P19-1092, https:\/\/aclanthology.org\/P19-1092","DOI":"10.18653\/v1\/P19-1092"},{"key":"6_CR24","unstructured":"Wang, H., et al.: HuaTuo: tuning llama model with Chinese medical knowledge (2023)"},{"key":"6_CR25","unstructured":"Wang, X., et\u00a0al.: CMB: a comprehensive medical benchmark in Chinese. arXiv preprint arXiv:2308.08833 (2023)"},{"key":"6_CR26","doi-asserted-by":"publisher","unstructured":"Wang, Y., et al.: Super-NaturalInstructions: generalization via declarative instructions on 1600+ NLP tasks. In: Goldberg, Y., Kozareva, Z., Zhang, Y. (eds.) Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 5085\u20135109. Association for Computational Linguistics, Abu Dhabi (2022). https:\/\/doi.org\/10.18653\/v1\/2022.emnlp-main.340, https:\/\/aclanthology.org\/2022.emnlp-main.340","DOI":"10.18653\/v1\/2022.emnlp-main.340"},{"key":"6_CR27","unstructured":"Wei, J., et al.: Finetuned language models are zero-shot learners. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=gEZrGCozdqR"},{"key":"6_CR28","unstructured":"Zhang, H., et al.: Huatuogpt, towards taming language models to be a doctor. arXiv preprint arXiv:2305.15075 (2023)"},{"key":"6_CR29","doi-asserted-by":"publisher","first-page":"74061","DOI":"10.1109\/ACCESS.2018.2883637","volume":"6","author":"S Zhang","year":"2018","unstructured":"Zhang, S., Zhang, X., Wang, H., Guo, L., Liu, S.: Multi-scale attentive interaction networks for Chinese medical question answer selection. IEEE Access 6, 74061\u201374071 (2018). https:\/\/doi.org\/10.1109\/ACCESS.2018.2883637","journal-title":"IEEE Access"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Zheng, Y., et al.: LLaMAFactory: unified efficient fine-tuning of 100+ language models. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations). Association for Computational Linguistics, Bangkok (2024). http:\/\/arxiv.org\/abs\/2403.13372","DOI":"10.18653\/v1\/2024.acl-demos.38"},{"key":"6_CR31","unstructured":"Zheng, Z., Liao, L., Deng, Y., Nie, L.: Building emotional support chatbots in the era of LLMs (2023)"}],"container-title":["Lecture Notes in Computer Science","Social Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-1151-5_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T16:01:19Z","timestamp":1738857679000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-1151-5_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819611508","9789819611515"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-1151-5_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"7 February 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICSR + InnoBiz","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Social Robotics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenzhen","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"socrob2024b","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.asianlp.sg\/conferences\/icsr2024\/web\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}