{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:17:09Z","timestamp":1780766229980,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":11,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFF0901003"],"award-info":[{"award-number":["2021YFF0901003"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62337001, U20A20229"],"award-info":[{"award-number":["62337001, U20A20229"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["SC5290005194"],"award-info":[{"award-number":["SC5290005194"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1145\/3589335.3651243","type":"proceedings-article","created":{"date-parts":[[2024,5,12]],"date-time":"2024-05-12T18:41:21Z","timestamp":1715539281000},"page":"1035-1038","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Towards Personalized Evaluation of Large Language Models with An Anonymous Crowd-Sourcing Platform"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9873-7681","authenticated-orcid":false,"given":"Mingyue","family":"Cheng","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0877-2681","authenticated-orcid":false,"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Data Science, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6421-2626","authenticated-orcid":false,"given":"Jiqian","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6956-5550","authenticated-orcid":false,"given":"Qi","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5491-3693","authenticated-orcid":false,"given":"Li","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9775-3046","authenticated-orcid":false,"given":"Xin","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7141-6580","authenticated-orcid":false,"given":"Liwei","family":"Song","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8061-7486","authenticated-orcid":false,"given":"Zhi","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1661-0420","authenticated-orcid":false,"given":"Zhenya","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4835-4102","authenticated-orcid":false,"given":"Enhong","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,5,13]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Yupeng Chang Xu Wang Jindong Wang Yuan Wu Linyi Yang Kaijie Zhu Hao Chen Xiaoyuan Yi Cunxiang Wang Yidong Wang et al. 2023. A survey on evaluation of large language models. ACM Transactions on Intelligent Systems and Technology (2023)."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3184558.3186905"},{"key":"e_1_3_2_2_4_1","volume-title":"C-eval: A multi-level multi-discipline chinese evaluation suite for foundation models. arXiv preprint arXiv:2305.08322","author":"Huang Yuzhen","year":"2023","unstructured":"Yuzhen Huang, Yuzhuo Bai, Zhihao Zhu, Junlei Zhang, Jinghan Zhang, Tangjun Su, Junteng Liu, Chuancheng Lv, Yikai Zhang, Jiayi Lei, et al. 2023. C-eval: A multi-level multi-discipline chinese evaluation suite for foundation models. arXiv preprint arXiv:2305.08322 (2023)."},{"key":"e_1_3_2_2_5_1","volume-title":"Reformulating Sequential Recommendation: Learning Dynamic User Interest with Content-enriched Language Modeling. arXiv preprint arXiv:2309.10435","author":"Jiang Junzhe","year":"2023","unstructured":"Junzhe Jiang, Shang Qu, Mingyue Cheng, and Qi Liu. 2023. Reformulating Sequential Recommendation: Learning Dynamic User Interest with Content-enriched Language Modeling. arXiv preprint arXiv:2309.10435 (2023)."},{"key":"e_1_3_2_2_6_1","volume-title":"Beyond Static Datasets: A Deep Interaction Approach to LLM Evaluation. arXiv preprint arXiv:2309.04369","author":"Li Jiatong","year":"2023","unstructured":"Jiatong Li, Rui Li, and Qi Liu. 2023. Beyond Static Datasets: A Deep Interaction Approach to LLM Evaluation. arXiv preprint arXiv:2309.04369 (2023)."},{"key":"e_1_3_2_2_7_1","volume-title":"Unlocking the potential of large language models for explainable recommendations. arXiv preprint arXiv:2312.15661","author":"Luo Yucong","year":"2023","unstructured":"Yucong Luo, Mingyue Cheng, Hao Zhang, Junyu Lu, and Enhong Chen. 2023. Unlocking the potential of large language models for explainable recommendations. arXiv preprint arXiv:2312.15661 (2023)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compedu.2016.03.017"},{"key":"e_1_3_2_2_9_1","volume-title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461","author":"Wang Alex","year":"2018","unstructured":"Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R Bowman. 2018. GLUE: A multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461 (2018)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2661829.2661998"},{"key":"e_1_3_2_2_11_1","unstructured":"Yan Zhuang Qi Liu Yuting Ning Weizhe Huang Rui Lv Zhenya Huang Guanhao Zhao Zheng Zhang Qingyang Mao Shijin Wang et al. 2023. Efficiently Measuring the Cognitive Ability of LLMs: An Adaptive Testing Perspective. arXiv preprint arXiv:2306.10512 (2023)."}],"event":{"name":"WWW '24: The ACM Web Conference 2024","location":"Singapore Singapore","acronym":"WWW '24","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Companion Proceedings of the ACM Web Conference 2024"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589335.3651243","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3589335.3651243","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:30:14Z","timestamp":1755822614000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589335.3651243"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":11,"alternative-id":["10.1145\/3589335.3651243","10.1145\/3589335"],"URL":"https:\/\/doi.org\/10.1145\/3589335.3651243","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]},"assertion":[{"value":"2024-05-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}