{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T07:12:37Z","timestamp":1769238757146,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819703159","type":"print"},{"value":"9789819703166","type":"electronic"}],"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\/978-981-97-0316-6_9","type":"book-chapter","created":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T19:02:19Z","timestamp":1707850939000},"page":"137-152","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["AGIBench: A Multi-granularity, Multimodal, Human-Referenced, Auto-Scoring Benchmark for\u00a0Large Language Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2521-4825","authenticated-orcid":false,"given":"Fei","family":"Tang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3911-9389","authenticated-orcid":false,"given":"Wanling","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6997-1448","authenticated-orcid":false,"given":"LuZhou","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3728-6837","authenticated-orcid":false,"given":"Jianfeng","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,2,14]]},"reference":[{"key":"9_CR1","unstructured":"Bubeck, S., et al.: Sparks of artificial general intelligence: early experiments with GPT-4 (2023)"},{"issue":"1","key":"9_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1037\/h0046743","volume":"54","author":"RB Cattell","year":"1963","unstructured":"Cattell, R.B.: Theory of fluid and crystallized intelligence: a critical experiment. J. Educ. Psychol. 54(1), 1 (1963)","journal-title":"J. Educ. Psychol."},{"key":"9_CR3","unstructured":"Cobbe, K., et al.: Training verifiers to solve math word problems (2021)"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Gardner, H.: The theory of multiple intelligences. Ann. Dyslexia 19\u201335 (1987)","DOI":"10.1007\/BF02648057"},{"key":"9_CR6","unstructured":"Hendrycks, D., et al.: Measuring mathematical problem solving with the math dataset. In: Thirty-Fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2) (2021)"},{"key":"9_CR7","unstructured":"Huang, Y., et al.: C-Eval: a multi-level multi-discipline Chinese evaluation suite for foundation models (2023)"},{"key":"9_CR8","first-page":"17","volume":"157","author":"S Legg","year":"2007","unstructured":"Legg, S., Hutter, M., et al.: A collection of definitions of intelligence. Front. Artif. Intell. Appl. 157, 17 (2007)","journal-title":"Front. Artif. Intell. Appl."},{"key":"9_CR9","unstructured":"Liang, P., et al.: Holistic evaluation of language models (2022)"},{"key":"9_CR10","unstructured":"Lu, P., et al.: Learn to explain: Multimodal reasoning via thought chains for science question answering. In: Advances in Neural Information Processing Systems, vol. 35, pp. 2507\u20132521 (2022)"},{"key":"9_CR11","unstructured":"Raji, I.D., Bender, E.M., Paullada, A., Denton, E., Hanna, A.: AI and the everything in the whole wide world benchmark. arXiv preprint arXiv:2111.15366 (2021)"},{"key":"9_CR12","unstructured":"Srivastava, A., et al.: Beyond the imitation game: quantifying and extrapolating the capabilities of language models. Trans. Mach. Learn. Res. (2023)"},{"key":"9_CR13","unstructured":"Sternberg, R.J.: The triarchic theory of intelligence (1997)"},{"key":"9_CR14","unstructured":"Wang, A., et al.: SuperGLUE: a stickier benchmark for general-purpose language understanding systems. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R.: GLUE: a multi-task benchmark and analysis platform for natural language understanding. In: International Conference on Learning Representations (2019)","DOI":"10.18653\/v1\/W18-5446"},{"issue":"3","key":"9_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3386252","volume":"53","author":"Y Wang","year":"2020","unstructured":"Wang, Y., Yao, Q., Kwok, J.T., Ni, L.M.: Generalizing from a few examples: a survey on few-shot learning. ACM Comput. Surv. (CSUR) 53(3), 1\u201334 (2020)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"9_CR17","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. In: Advances in Neural Information Processing Systems, vol. 35, pp. 24824\u201324837 (2022)"},{"key":"9_CR18","unstructured":"Zhang, X., Li, C., Zong, Y., Ying, Z., He, L., Qiu, X.: Evaluating the performance of large language models on Gaokao benchmark (2023)"},{"key":"9_CR19","unstructured":"Zheng, L., et al.: Judging LLM-as-a-judge with MT-bench and chatbot arena (2023)"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Zhong, W., et al.: AGIEval: a human-centric benchmark for evaluating foundation models (2023)","DOI":"10.18653\/v1\/2024.findings-naacl.149"}],"container-title":["Lecture Notes in Computer Science","Benchmarking, Measuring, and Optimizing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-0316-6_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T06:31:44Z","timestamp":1731306704000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-0316-6_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819703159","9789819703166"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-0316-6_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"14 February 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Bench","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Benchmarking, Measuring and Optimization","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sanya","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 December 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bench2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.benchcouncil.org\/bench2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"HotCRP","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"20","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"11","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"55% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4.75","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}