{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T23:20:11Z","timestamp":1756682411903,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819794362"},{"type":"electronic","value":"9789819794379"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-981-97-9437-9_6","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T16:27:22Z","timestamp":1730392042000},"page":"67-79","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["What is the\u00a0Best Model? Application-Driven Evaluation for\u00a0Large Language Models"],"prefix":"10.1007","author":[{"given":"Shiguo","family":"Lian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaikai","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinhui","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuejiao","family":"Lei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bikun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoxiang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"6_CR1","unstructured":"Austin, J., et al.: Program synthesis with large language models. arXiv preprint arXiv:2108.07732 (2021)"},{"key":"6_CR2","unstructured":"Bai, J., et al.: Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Z., Li, S., Smiley, C., Ma, Z., Shah, S., Wang, W.Y.: Convfinqa: exploring the chain of numerical reasoning in conversational finance question answering. arXiv preprint arXiv:2210.03849 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.421"},{"key":"6_CR4","unstructured":"OC Contributors: Opencompass: A universal evaluation platform for foundation models (2023). https:\/\/github.com\/open-compass\/opencompass"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Guha, N., et al.: Legalbench: a collaboratively built benchmark for measuring legal reasoning in large language models. In: Advances in Neural Information Processing Systems, vol. 36 (2024)","DOI":"10.2139\/ssrn.4583531"},{"key":"6_CR6","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1007\/978-3-031-44696-2_33","volume-title":"NLPCC 2023","author":"G Guo","year":"2023","unstructured":"Guo, G., Yang, J., Lu, F., Qin, J., Tang, T., Zhao, W.X.: Towards effective ancient Chinese translation: dataset, model, and evaluation. In: Liu, F., Duan, N., Xu, Q., Hong, Y. (eds.) NLPCC 2023. LNCS, vol. 14303, pp. 416\u2013427. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-44696-2_33"},{"key":"6_CR7","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1007\/978-3-031-17120-8_14","volume-title":"NLPCC 2022","author":"C Han","year":"2022","unstructured":"Han, C., Zhang, J., Li, X., Xu, G., Peng, W., Zeng, Z.: DuEE-Fin: a large-scale dataset for document-level event extraction. In: Lu, W., Huang, S., Hong, Y., Zhou, X. (eds.) NLPCC 2022. LNCS, vol. 13551, pp. 172\u2013183. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-17120-8_14"},{"key":"6_CR8","unstructured":"Hendrycks, D., et al.: Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300 (2020)"},{"key":"6_CR9","unstructured":"Huang, Y., et al.: C-eval: a multi-level multi-discipline Chinese evaluation suite for foundation models. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"6_CR10","unstructured":"Kaplan, J., et al.: Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)"},{"key":"6_CR11","unstructured":"Liang, P., et al.: Holistic evaluation of language models. arXiv preprint arXiv:2211.09110 (2022)"},{"key":"6_CR12","unstructured":"Liu, C., et al.: M3KE: a massive multi-level multi-subject knowledge evaluation benchmark for Chinese large language models. arXiv preprint arXiv:2305.10263 (2023)"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Liu, C., et al.: Openeval: benchmarking Chinese LLMs across capability, alignment and safety. arXiv preprint arXiv:2403.12316 (2024)","DOI":"10.18653\/v1\/2024.acl-demos.19"},{"key":"6_CR14","unstructured":"Sawada, T., et al.: ARB: advanced reasoning benchmark for large language models. In: The 3rd Workshop on Mathematical Reasoning and AI at NeurIPS 2023 (2023)"},{"key":"6_CR15","unstructured":"Shen, Y., et al.: Taskbench: benchmarking large language models for task automation. arXiv preprint arXiv:2311.18760 (2023)"},{"issue":"7972","key":"6_CR16","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","volume":"620","author":"K Singhal","year":"2023","unstructured":"Singhal, K., et al.: Large language models encode clinical knowledge. Nature 620(7972), 172\u2013180 (2023)","journal-title":"Nature"},{"key":"6_CR17","unstructured":"Srivastava, A., et al.: Beyond the imitation game: quantifying and extrapolating the capabilities of language models. arXiv preprint arXiv:2206.04615 (2022)"},{"key":"6_CR18","first-page":"24824","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":"6_CR19","unstructured":"Zeng, H.: Measuring massive multitask Chinese understanding. arXiv preprint arXiv:2304.12986 (2023)"},{"key":"6_CR20","unstructured":"Zhang, B., et al.: Evaluating and improving tool-augmented computation-intensive math reasoning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-9437-9_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T16:28:10Z","timestamp":1730392090000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-9437-9_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9789819794362","9789819794379"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-9437-9_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hangzhou","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":"2 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2024\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}