{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T18:50:19Z","timestamp":1782154219638,"version":"3.54.5"},"reference-count":41,"publisher":"Elsevier BV","issue":"1","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100008868","name":"Jiangsu Province Department of Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008868","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012246","name":"Priority Academic Program Development of Jiangsu Higher Education Institutions","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012246","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62106165"],"award-info":[{"award-number":["62106165"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Processing & Management"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.ipm.2026.104928","type":"journal-article","created":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T04:10:39Z","timestamp":1781842239000},"page":"104928","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["VotingBench : Evaluating generative capabilities of Large Language Models via voting games"],"prefix":"10.1016","volume":"64","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7643-0646","authenticated-orcid":false,"given":"Jiale","family":"Mao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4385-8675","authenticated-orcid":false,"given":"Jinyi","family":"Zu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1077-9033","authenticated-orcid":false,"given":"Ziqiang","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.ipm.2026.104928_b1","series-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"10.1016\/j.ipm.2026.104928_b2","series-title":"Qwen technical report","author":"Bai","year":"2023"},{"key":"10.1016\/j.ipm.2026.104928_b3","series-title":"MT-bench-101: A fine-grained benchmark for evaluating large language models in multi-turn dialogues","author":"Bai","year":"2024"},{"key":"10.1016\/j.ipm.2026.104928_b4","doi-asserted-by":"crossref","unstructured":"Bowman, S. R., Angeli, G., Potts, C., & Manning, C. D. (2015). A large annotated corpus for learning natural language inference. In Conference on empirical methods in natural language processing.","DOI":"10.18653\/v1\/D15-1075"},{"issue":"1","key":"10.1016\/j.ipm.2026.104928_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2025.104337","article-title":"Custom training data: Aligning model distribution via prefix-guided preference data synthesis","volume":"63","author":"Chen","year":"2026","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.104928_b6","series-title":"Training verifiers to solve math word problems","author":"Cobbe","year":"2021"},{"key":"10.1016\/j.ipm.2026.104928_b7","series-title":"GameBench: Evaluating strategic reasoning abilities of LLM agents","author":"Costarelli","year":"2024"},{"key":"10.1016\/j.ipm.2026.104928_b8","series-title":"DeepSeek-R1: Incentivizing reasoning capability in LLMs via reinforcement learning","author":"DeepSeek-AI","year":"2025"},{"key":"10.1016\/j.ipm.2026.104928_b9","series-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"10.1016\/j.ipm.2026.104928_b10","series-title":"Length-controlled AlpacaEval: A simple way to debias automatic evaluators","author":"Dubois","year":"2024"},{"key":"10.1016\/j.ipm.2026.104928_b11","series-title":"Seed1.5-VL technical report","author":"Guo","year":"2025"},{"key":"10.1016\/j.ipm.2026.104928_b12","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2026.104704","article-title":"Toward better pragmatic tagging of peer review: Enhancing benchmark datasets via human-in-the-loop multi-agent collaboration","author":"He","year":"2026","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.104928_b13","series-title":"Measuring massive multitask language understanding","author":"Hendrycks","year":"2020"},{"key":"10.1016\/j.ipm.2026.104928_b14","series-title":"C-eval: A multi-level multi-discipline Chinese evaluation suite for foundation models","author":"Huang","year":"2023"},{"key":"10.1016\/j.ipm.2026.104928_b15","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2025.104225","article-title":"PaperEval: A universal, quantitative, and explainable paper evaluation method powered by a multi-agent system","volume":"62","author":"Huang","year":"2025","journal-title":"Information Processing & Management"},{"issue":"6","key":"10.1016\/j.ipm.2026.104928_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2025.104239","article-title":"Red teaming large language models: A comprehensive review and critical analysis","volume":"62","author":"Jabbar","year":"2025","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.104928_b17","series-title":"Large language model strategic reasoning evaluation through behavioral game theory","author":"Jia","year":"2025"},{"key":"10.1016\/j.ipm.2026.104928_b18","series-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"10.1016\/j.ipm.2026.104928_b19","doi-asserted-by":"crossref","unstructured":"Liu, Y., Duan, H., Zhang, Y., Li, B., Zhang, S., Zhao, W., Yuan, Y., Wang, J., He, C., Liu, Z., Chen, K., & Lin, D. (2023). MMBench: Is Your Multi-modal Model an All-around Player?. In European conference on computer vision.","DOI":"10.1007\/978-3-031-72658-3_13"},{"issue":"5","key":"10.1016\/j.ipm.2026.104928_b20","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2024.103809","article-title":"Are LLMs good at structured outputs? A benchmark for evaluating structured output capabilities in LLMs","volume":"61","author":"Liu","year":"2024","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.104928_b21","series-title":"AgentBench: Evaluating LLMs as agents","author":"Liu","year":"2023"},{"key":"10.1016\/j.ipm.2026.104928_b22","series-title":"DeepSeek-VL: Towards real-world vision-language understanding","author":"Lu","year":"2024"},{"key":"10.1016\/j.ipm.2026.104928_b23","doi-asserted-by":"crossref","DOI":"10.1016\/j.cola.2025.101351","article-title":"Evaluating quantized large language models for code generation on low-resource language benchmarks","volume":"84","author":"Nyamsuren","year":"2025","journal-title":"Journal of Computer Languages"},{"key":"10.1016\/j.ipm.2026.104928_b24","doi-asserted-by":"crossref","unstructured":"Richardson, M., Burges, C. J. C. Renshaw, E. (2013). MCTest: A Challenge Dataset for the Open-Domain Machine Comprehension of Text. In Conference on empirical methods in natural language processing.","DOI":"10.18653\/v1\/D13-1020"},{"key":"10.1016\/j.ipm.2026.104928_b25","series-title":"DeepSeek-V2: A strong, economical, and efficient mixture-of-experts language model","author":"Shao","year":"2024"},{"key":"10.1016\/j.ipm.2026.104928_b26","series-title":"Beyond the imitation game: Quantifying and extrapolating the capabilities of language models","author":"Srivastava","year":"2022"},{"key":"10.1016\/j.ipm.2026.104928_b27","series-title":"ERNIE 3.0: Large-scale knowledge enhanced pre-training for language understanding and generation","author":"Sun","year":"2021"},{"issue":"4","key":"10.1016\/j.ipm.2026.104928_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2025.104147","article-title":"Retriever-generator-verification: A novel approach to enhancing factual coherence in open-domain question answering","volume":"62","author":"Sun","year":"2025","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.104928_b29","series-title":"InternVL2: Better than the best\u2014Expanding performance boundaries of open-source multimodal models with the progressive scaling strategy","author":"Team","year":"2024"},{"key":"10.1016\/j.ipm.2026.104928_b30","series-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023"},{"issue":"5","key":"10.1016\/j.ipm.2026.104928_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2025.104145","article-title":"Knowledge graph validation by integrating LLMs and human-in-the-loop","volume":"62","author":"Tsaneva","year":"2025","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.104928_b32","series-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"10.1016\/j.ipm.2026.104928_b33","series-title":"Large language models are not fair evaluators","author":"Wang","year":"2023"},{"key":"10.1016\/j.ipm.2026.104928_b34","series-title":"SuperGLUE: A stickier benchmark for general-purpose language understanding systems","author":"Wang","year":"2019"},{"key":"10.1016\/j.ipm.2026.104928_b35","series-title":"BlackboxNLP@eMNLP","article-title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding","author":"Wang","year":"2018"},{"key":"10.1016\/j.ipm.2026.104928_b36","article-title":"A survey on multimodal large language models","volume":"11","author":"Yin","year":"2023","journal-title":"National Science Review"},{"key":"10.1016\/j.ipm.2026.104928_b37","series-title":"MMT-bench: A comprehensive multimodal benchmark for evaluating large vision-language models towards multitask AGI","author":"Ying","year":"2024"},{"key":"10.1016\/j.ipm.2026.104928_b38","series-title":"ChatGLM: A family of large language models from GLM-130b to GLM-4 all tools","author":"Zeng","year":"2024"},{"key":"10.1016\/j.ipm.2026.104928_b39","series-title":"Judging LLM-as-a-judge with MT-bench and chatbot arena","author":"Zheng","year":"2023"},{"key":"10.1016\/j.ipm.2026.104928_b40","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2025.104864","article-title":"How well do multimodal LLMs interpret CT scans? An auto-evaluation framework for analyses","volume":"168","author":"Zhu","year":"2025","journal-title":"Journal of Biomedical Informatics"},{"key":"10.1016\/j.ipm.2026.104928_b41","article-title":"A quasi-experimental analysis of capabilities and limitations of generative AI in academic content evaluation in social sciences","volume":"63","author":"Zhu","year":"2026","journal-title":"Information Processing & Management"}],"container-title":["Information Processing & Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457326003195?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457326003195?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T18:10:58Z","timestamp":1782151858000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0306457326003195"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":41,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2027,1]]}},"alternative-id":["S0306457326003195"],"URL":"https:\/\/doi.org\/10.1016\/j.ipm.2026.104928","relation":{},"ISSN":["0306-4573"],"issn-type":[{"value":"0306-4573","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"VotingBench : Evaluating generative capabilities of Large Language Models via voting games","name":"articletitle","label":"Article Title"},{"value":"Information Processing & Management","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ipm.2026.104928","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104928"}}