{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T22:01:11Z","timestamp":1743112871592,"version":"3.40.3"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031703775"},{"type":"electronic","value":"9783031703782"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-70378-2_15","type":"book-chapter","created":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T09:02:05Z","timestamp":1725181325000},"page":"240-255","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Merge Sort Based Ranking System for\u00a0the\u00a0Evaluation of\u00a0Large Language Models"],"prefix":"10.1007","author":[{"given":"Chenchen","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linfeng","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunyi","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoxin","family":"Huan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengfu","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xudong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,22]]},"reference":[{"issue":"3","key":"15_CR1","doi-asserted-by":"publisher","first-page":"839","DOI":"10.2466\/pr0.1997.80.3.839","volume":"80","author":"KJ Berry","year":"1997","unstructured":"Berry, K.J., Mielke, P.W., Jr.: Spearman\u2019s footrule as a measure of agreement. Psychol. Rep. 80(3), 839\u2013846 (1997)","journal-title":"Psychol. Rep."},{"unstructured":"Bommasani, R., et\u00a0al.: On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258 (2021)","key":"15_CR2"},{"key":"15_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3641289","volume":"15","author":"Y Chang","year":"2023","unstructured":"Chang, Y., et al.: A survey on evaluation of large language models. ACM Trans. Intell. Syst. Technol. 15, 1\u201345 (2023)","journal-title":"ACM Trans. Intell. Syst. Technol."},{"unstructured":"Opencompass Contributors.: Opencompass: a universal evaluation platform for foundation models (2023). https:\/\/github.com\/open-compass\/opencompass","key":"15_CR4"},{"issue":"8","key":"15_CR5","first-page":"242","volume":"22","author":"AE Elo","year":"1967","unstructured":"Elo, A.E.: The proposed USCF rating system, its development, theory, and applications. Chess Life 22(8), 242\u2013247 (1967)","journal-title":"Chess Life"},{"unstructured":"Hendrycks, D., et al.: Measuring massive multitask language understanding. In: Proceedings of the International Conference on Learning Representations (ICLR) (2021)","key":"15_CR6"},{"unstructured":"Huang, Y., et\u00a0al.: C-eval: a multi-level multi-discipline Chinese evaluation suite for foundation models. In: Advances in Neural Information Processing Systems, vol. 36 (2024)","key":"15_CR7"},{"unstructured":"Li, R., Patel, T., Du, X.: PRD: peer rank and discussion improve large language model based evaluations. arXiv preprint arXiv:2307.02762 (2023)","key":"15_CR8"},{"unstructured":"Liang, P., et al.: Holistic evaluation of language models. arXiv:2211.09110 (2023)","key":"15_CR9"},{"unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)","key":"15_CR10"},{"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)","key":"15_CR11","DOI":"10.3115\/1073083.1073135"},{"unstructured":"Big-Bench authors.: Beyond the imitation game: quantifying and extrapolating the capabilities of language models. Trans. Mach. Learn. Res. (2023)","key":"15_CR12"},{"unstructured":"Wang, P., et al.: Large language models are not fair evaluators. arXiv preprint arXiv:2305.17926 (2023)","key":"15_CR13"},{"unstructured":"Wei, J., et\u00a0al.: Emergent abilities of large language models. arXiv preprint arXiv:2206.07682 (2022)","key":"15_CR14"},{"unstructured":"Wikipedia: Round-robin tournament (2023). https:\/\/en.wikipedia.org\/wiki\/Round-robin_tournament","key":"15_CR15"},{"unstructured":"Xu, C., et al.: WizardLM: empowering large language models to follow complex instructions. arXiv preprint arXiv:2304.12244 (2023)","key":"15_CR16"},{"unstructured":"Xu, L., et al.: Superclue: a comprehensive Chinese large language model benchmark. arXiv preprint arXiv:2307.15020 (2023)","key":"15_CR17"},{"unstructured":"Zhang, Y., et al.: Llmeval: a preliminary study on how to evaluate large language models. arXiv preprint arXiv:2312.07398 (2023)","key":"15_CR18"},{"unstructured":"Zheng, L., et\u00a0al.: Judging LLM-as-a-judge with MT-bench and chatbot arena. In: Advances in Neural Information Processing Systems, vol. 36 (2024)","key":"15_CR19"},{"doi-asserted-by":"crossref","unstructured":"Zhong, W., et al.: AGIEval: a human-centric benchmark for evaluating foundation models. arXiv preprint arXiv:2304.06364 (2023)","key":"15_CR20","DOI":"10.18653\/v1\/2024.findings-naacl.149"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70378-2_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T09:05:11Z","timestamp":1725181511000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70378-2_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031703775","9783031703782"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70378-2_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"22 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vilnius","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","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":"8 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2024.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}