{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T22:59:09Z","timestamp":1781045949696,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819572502","type":"print"},{"value":"9789819572519","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-7251-9_15","type":"book-chapter","created":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T22:31:09Z","timestamp":1781044269000},"page":"210-225","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TCM-Eval: A Multi-dimensional Benchmark Framework for\u00a0Evaluating Large Language Models in\u00a0Traditional Chinese Medicine"],"prefix":"10.1007","author":[{"given":"Meihan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuqian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanshuo","family":"Xing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengwei","family":"Zhuang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangyu","family":"Ji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,1]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Yang, H., et al.: LLM-MedQA: Enhancing Medical Question Answering Through Case Studies in Large Language Models. arXiv preprint arXiv:2501.05464 (2024)","DOI":"10.1109\/IJCNN64981.2025.11228647"},{"key":"15_CR2","unstructured":"Pal, A., Umapathi, L. K., Sankarasubbu, M.: MedMCQA: A large-scale multi-subject multi-choice dataset for medical domain question answering. In: Proceedings of the Conference on Health, Inference, and Learning, pp. 248\u2013260. PMLR (2022)"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Jin, Q., Dhingra, B., Liu, Z., Cohen, W.W., Lu, X.: PubMedQA: A Dataset for Biomedical Research Question Answering. arXiv preprint arXiv:1909.06146 (2019)","DOI":"10.18653\/v1\/D19-1259"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Cai, Y., et al.: MedBench: a large-scale chinese benchmark for evaluating medical large language models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 16, pp. 17709\u201317717 (2024)","DOI":"10.1609\/aaai.v38i16.29723"},{"key":"15_CR5","unstructured":"Yue, W., et al.: TCMBench: A Comprehensive Benchmark for Evaluating Large Language Models in Traditional Chinese Medicine. arXiv preprint arXiv:2406.01126 (2024)"},{"key":"15_CR6","unstructured":"Huang, T., et al.: TCM-3CEval: A Triaxial Benchmark for Assessing Responses from Large Language Models in Traditional Chinese Medicine. arXiv preprint arXiv:2503.07041 (2025)"},{"key":"15_CR7","unstructured":"Kong, S., Yang, X., Wei, Y., et al.: MTCMB: A Multi-Task Benchmark Framework for Evaluating LLMs on Knowledge, Reasoning, and Safety in Traditional Chinese Medicine. arXiv preprint arXiv:2506.01252 (2025)"},{"key":"15_CR8","unstructured":"National Administration of Traditional Chinese Medicine: National Licensed TCM Practitioner Qualification Examination Syllabus (2023)"},{"key":"15_CR9","unstructured":"Ministry of Human Resources and Social Security: TCM Professional Technical Qualification Examination Guidelines (2022)"},{"key":"15_CR10","unstructured":"National Health Commission: Assistant TCM Practitioner Qualification Examination Standards (2023)"},{"key":"15_CR11","unstructured":"Zhu, W., Yue, W., Wang, X.: ShenNong-TCM: A Traditional Chinese Medicine Large Language Model. GitHub repository (2023). https:\/\/github.com\/michael-wzhu\/ShenNong-TCM-LLM, Accessed 13 July 2025"},{"key":"15_CR12","unstructured":"Traditional-Chinese-Medicine-Dataset-SFT (2024). https:\/\/huggingface.co\/datasets\/SylvanL\/Traditional-Chinese-Medicine-Dataset-SFT, Accessed 13 July 2025"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"15_CR14","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Proceedings of the ACL-04 Workshop: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"15_CR15","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K. Q., Artzi, Y.: BERTScore: Evaluating Text Generation with BERT. arXiv preprint arXiv:1904.09675 (2019)"},{"key":"15_CR16","unstructured":"Devlin, J., Chang, M. W., Lee, K., Toutanova, K.: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv preprint arXiv:1810.04805 (2019)"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Jiang, H.: Short-Text semantic similarity model of BERT-Based Siamese network. In: Proceedings of the 10th International Conference on Wireless Communication and Sensor Networks, pp. 145\u2013149 (2023)","DOI":"10.1145\/3585967.3585994"},{"key":"15_CR18","unstructured":"Guo, D., et al.: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. arXiv preprint arXiv:2501.12948 (2025)"},{"key":"15_CR19","unstructured":"ByteDance: Doubao Large Language Model (2023). https:\/\/www.doubao.com, Accessed 13 July 2025"},{"key":"15_CR20","unstructured":"Yang, A., et al.: Qwen3 Technical Report. arXiv preprint arXiv:2505.09388 (2025)"},{"key":"15_CR21","unstructured":"Zhipu AI: Zhipu-4-Plus Technical Report. Technical Report (2024). https:\/\/www.zhipuai.cn\/, Accessed 13 July 2025"},{"key":"15_CR22","unstructured":"Anthropic: Claude 3 Model Family: Technical Overview and Capabilities. Technical Report (2024). https:\/\/www.anthropic.com\/news\/claude-3-family, Accessed 13 July 2025"},{"key":"15_CR23","unstructured":"OpenAI: GPT-4 Technical Report. Technical Report (2023). https:\/\/cdn.openai.com\/papers\/gpt-4.pdf, Accessed 13 July 2025"},{"key":"15_CR24","unstructured":"Touvron, H., et al.: Llama: Open and Efficient Foundation Language Models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"15_CR25","unstructured":"Baichuan Intelligence: Baichuan 3 Technical Report. Technical Report (2024). https:\/\/www.baichuan-ai.com\/, Accessed 13 July 2025"},{"key":"15_CR26","unstructured":"iFLYTEK: SparkDesk: The Large Language Model by iFLYTEK. Technical Report (2023). https:\/\/xinghuo.xfyun.cn\/, Accessed 13 July 2025"},{"key":"15_CR27","unstructured":"Wang, H., et al.: Huatuo: Tuning Llama Model with Chinese Medical Knowledge. arXiv preprint arXiv:2304.06975 (2023)"},{"key":"15_CR28","unstructured":"Liao, Y., Jiang, S., Wang, Y., Wang, Y.: MING-MOE: Enhancing Medical Multi-Task Learning in Large Language Models with Sparse Mixture of Low-Rank Adapter Experts. arXiv preprint arXiv:2404.09027 (2024)"},{"key":"15_CR29","unstructured":"Yan, X., Xue, D.: Sunsimiao: Chinese Medicine LLM. GitHub repository (2023). https:\/\/github.com\/thomas-yanxin\/Sunsimiao, Accessed 13 July 2025"},{"key":"15_CR30","unstructured":"Wisediag: Wisediag: AI-Powered Medical Diagnostics Platform. Technical Report (2024). https:\/\/www.wisediag.com\/, Accessed 13 July 2025"},{"key":"15_CR31","unstructured":"Wei, S., et al.: Biancang: A Traditional Chinese Medicine Large Language Model. arXiv preprint arXiv:2411.11027 (2024)"},{"key":"15_CR32","doi-asserted-by":"publisher","unstructured":"Jia, Y., Ji, X., Wang, X., et al.: Qibo: a large language model for traditional Chinese medicine. Expert Syst. Appl. 284, 127672 (2025). https:\/\/doi.org\/10.1016\/j.eswa.2025.127672","DOI":"10.1016\/j.eswa.2025.127672"},{"key":"15_CR33","doi-asserted-by":"crossref","unstructured":"Yang, S., et al.: Zhongjing: enhancing the Chinese medical capabilities of large language models through expert feedback and real-world multi-turn dialogue. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 17, pp. 19368\u201319376 (2024)","DOI":"10.1609\/aaai.v38i17.29907"}],"container-title":["Lecture Notes in Computer Science","Web Information Systems Engineering \u2013 WISE 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-7251-9_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T22:31:17Z","timestamp":1781044277000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-7251-9_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819572502","9789819572519"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-7251-9_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 May 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"WISE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Web Information Systems Engineering","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Marrakech","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Morocco","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":"15 December 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 December 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":"wise2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/wise2025.ficloud.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}