{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T19:01:44Z","timestamp":1762455704046,"version":"build-2065373602"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2024YFC3308200"],"award-info":[{"award-number":["2024YFC3308200"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62525606","62441239","62477044"],"award-info":[{"award-number":["62525606","62441239","62477044"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Technologies R&D Program of Anhui Province","award":["202423k09020039"],"award-info":[{"award-number":["202423k09020039"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Young Elite Scientists Sponsorship"},{"name":"CAST","award":["2024QNRC001"],"award-info":[{"award-number":["2024QNRC001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tpami.2025.3598031","type":"journal-article","created":{"date-parts":[[2025,8,12]],"date-time":"2025-08-12T18:01:55Z","timestamp":1755021715000},"page":"11785-11801","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Benchmarking via Bias-Bounded Subset Selection"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7351-377X","authenticated-orcid":false,"given":"Yan","family":"Zhuang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junhao","family":"Yu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6956-5550","authenticated-orcid":false,"given":"Qi","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxuan","family":"Sun","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8877-6927","authenticated-orcid":false,"given":"Jiatong","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1661-0420","authenticated-orcid":false,"given":"Zhenya","family":"Huang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4835-4102","authenticated-orcid":false,"given":"Enhong","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3641289"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06792-0"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3462293"},{"key":"ref5","article-title":"Beyond the imitation game: Quantifying and extrapolating the capabilities of language models","author":"Srivastava","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref6","article-title":"Holistic evaluation of language models","author":"Liang","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"article-title":"Alpacaeval: An automatic evaluator of instruction-following models","year":"2023","author":"Li","key":"ref7"},{"key":"ref8","first-page":"28072","article-title":"Emergent and predictable memorization in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Biderman","year":"2023"},{"key":"ref9","article-title":"AM-ELO: A stable framework for arena-based LLM evaluation","volume-title":"Proc. Forty-second Int. Conf. Mach. Learn.","author":"Liu","year":"2025"},{"key":"ref10","first-page":"34303","article-title":"tinyBenchmarks: Evaluating LLMs with fewer examples","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Polo","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3050464"},{"article-title":"metabench\u2013 a sparse benchmark to measure general ability in large language models","year":"2024","author":"Kipnis","key":"ref12"},{"key":"ref13","article-title":"Position: AI evaluation should learn from how we test humans","volume-title":"Proc. 42nd Int. Conf. Mach. Learn. Position Paper Track","author":"Zhuang","year":"2025"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.346"},{"key":"ref15","article-title":"Measuring massive multitask language understanding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hendrycks","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41498-5_2"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.468"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2023.0159"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.88"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref21","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref22","article-title":"BERTScore: Evaluating text generation with bert","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2020"},{"article-title":"Rethinking large language model architectures for sequential recommendations","year":"2024","author":"Wang","key":"ref23"},{"key":"ref24","first-page":"16773","article-title":"Automated evaluation of retrieval-augmented language models with task-specific exam generation","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","volume":"235","author":"Guinet","year":"2024"},{"key":"ref25","first-page":"2397","article-title":"Pythia: A suite for analyzing large language models across training and scaling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Biderman","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.503"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.139"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-long.95"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.4324\/9780203056615"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605269"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2849989"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16968"},{"key":"ref33","first-page":"5753","article-title":"Active testing: Sample-efficient model evaluation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kossen","year":"2021"},{"article-title":"Survey of computerized adaptive testing: A machine learning perspective","year":"2024","author":"Liu","key":"ref34"},{"key":"ref35","article-title":"Active learning for convolutional neural networks: A core-set approach","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sener","year":"2018"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2750672"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1111\/j.1745-3992.2003.tb00136.x"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TLT.2023.3253215"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.2297711"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.eval4nlp-1.3"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1049"},{"key":"ref42","first-page":"95","article-title":"Graded response models","volume-title":"Handbook of Item Response Theory","author":"Samejima","year":"2016"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1260"},{"key":"ref45","first-page":"6950","article-title":"Coresets for data-efficient training of machine learning models","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Mirzasoleiman","year":"2020"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.79"},{"volume-title":"Submodular Functions and Optimization","year":"2005","author":"Fujishige","key":"ref47"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2511748"},{"issue":"1","key":"ref49","first-page":"1","article-title":"Demonstrating the difference between classical test theory and item response theory using derived test data","volume":"1","author":"Magno","year":"2009","journal-title":"Int. J. Educ. Psychol. Assessment"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/BF01588971"},{"article-title":"Physics of language models: Part 1, learning hierarchical language structures","year":"2023","author":"Allen-Zhu","key":"ref51"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"article-title":"Training verifiers to solve math word problems","year":"2021","author":"Cobbe","key":"ref53"},{"key":"ref54","article-title":"Measuring mathematical problem solving with the math dataset","volume-title":"Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks","volume":"1.","author":"Hendrycks","year":"2021"},{"key":"ref55","article-title":"LegalBench: A collaboratively built benchmark for measuring legal reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Guha","year":"2024"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1206"},{"key":"ref57","article-title":"RAFT: A real-world few-shot text classification benchmark","volume-title":"Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks","volume":"1","author":"Alex","year":"2021"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0850"},{"article-title":"holistic analysis of hallucination in GPT-4V (ision): Bias and interference challenges","year":"2023","author":"Cui","key":"ref60"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.187"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/1281192.1281239"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0121012"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3201037"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-023-4239-4"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.3102\/10769986221129847"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.2307\/2332226"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/FUZZY.1995.409976"},{"key":"ref70","article-title":"Proving test set contamination for black-box language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Oren","year":"2023"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531928"},{"article-title":"Efficiently measuring the cognitive ability of LLMs: An adaptive testing perspective","year":"2023","author":"Zhuang","key":"ref72"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1177\/002194366900600202"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045882"},{"article-title":"HalluDial: A large-scale benchmark for automatic dialogue-level hallucination evaluation","year":"2024","author":"Luo","key":"ref75"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511817106"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.2307\/1969027"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546921"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11230086\/11123151.pdf?arnumber=11123151","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T18:53:27Z","timestamp":1762455207000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11123151\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":78,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3598031","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}