{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T15:42:23Z","timestamp":1758123743825,"version":"3.40.4"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,16]]},"DOI":"10.1109\/ictc62082.2024.10826596","type":"proceedings-article","created":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T19:40:10Z","timestamp":1736883610000},"page":"1503-1507","source":"Crossref","is-referenced-by-count":1,"title":["Harnessing LLMs for VQA: A Prompted Benchmark with Animate\/Inanimate Keywords"],"prefix":"10.1109","author":[{"given":"Chanwoo","family":"Lee","sequence":"first","affiliation":[{"name":"Seoul Woman's University,Dept. of Software Convergence,Seoul,South Korea"}]},{"given":"Hyunjeong","family":"Lee","sequence":"additional","affiliation":[{"name":"Hanbat National University,Dept. of Computer Engineering,Daejeon,South Korea"}]},{"given":"Minsang","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea University,Dept. of Computer Science and Engineering,Seoul,South Korea"}]},{"given":"Hyun","family":"Kim","sequence":"additional","affiliation":[{"name":"Electronics and Telecommunications Research Institute,Superintelligence Creative Research Lab.,Daejeon,South Korea"}]},{"given":"Haneol","family":"Jang","sequence":"additional","affiliation":[{"name":"Hanbat National University,Dept. of Computer Engineering,Daejeon,South Korea"}]},{"given":"Cheoneum","family":"Park","sequence":"additional","affiliation":[{"name":"Hanbat National University,Dept. of Computer Engineering,Daejeon,South Korea"}]}],"member":"263","reference":[{"volume-title":"Scaling laws for neural language models","year":"2020","author":"Kaplan","key":"ref1"},{"key":"ref2","article-title":"KMMLU: measuring massive multitask language understanding in Korean","author":"Son","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","first-page":"422","article-title":"KorNLI and KorSTS: new benchmark datasets for Korean natural language understanding","volume-title":"T. Cohn","author":"Ham","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00661"},{"key":"ref5","article-title":"Measuring massive multitask language understanding","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hendrycks","year":"2021"},{"key":"ref6","first-page":"3335","article-title":"CLIcK: A benchmark dataset of cultural and linguistic intelligence in Korean","volume-title":"Turin, Italy: ELRA and ICCL, May 2024, in Proc. 2024 Joint Int. Conf. Comput. Linguistics, Lang. Resources Eval. (LREC-COLING 2024)","author":"Kim"},{"key":"ref7","article-title":"A multitask benchmark for Korean legal language understanding and judgement prediction","volume-title":"Proc. Thirty-Sixth Conf. Neural Inf. Process. Syst. Datasets and Benchmarks Track","author":"Hwang","year":"2022"},{"key":"ref8","article-title":"KorNAT: LLM alignment benchmark for Korean social Values and common knowledge","author":"Lee","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"C-EVAL: a multilevel multi-discipline Chinese evaluation suite for foundation models","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst. Red Hook","author":"Huang","year":"2024"},{"issue":"16","key":"ref10","first-page":"18099","article-title":"Xiezhi: an ever-updating benchmark for holistic domain knowledge evaluation","volume":"38","author":"Gu","year":"2024","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref11","article-title":"Judging LLM-as-a-Judge with MT-Bench and chatbot arena","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst. Red Hook","author":"Zheng","year":"2024"},{"key":"ref12","article-title":"TaskBench: benchmarking large language models for task automation","author":"Shen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Planbench: an extensible benchmark for evaluating large language models on planning and reasoning about change","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst. Red Hook","author":"Valmeekam","year":"2024"},{"key":"ref14","article-title":"MMT-Bench: A comprehensive multimodal benchmark for evaluating large vision-language models towards multitask AGI","author":"Ying","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref16","first-page":"2333","article-title":"Generate then select: Open-ended visual question answering guided by world knowledge","volume-title":"Findings of the Association for Computational Linguistics: ACL 2023","author":"Fu"},{"key":"ref17","article-title":"Modular visual question answering via code generation","author":"Subramanian","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Microsoft COCO: common objects in context","author":"Lin","year":"2015","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00517"},{"key":"ref21","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann","year":"2022","journal-title":"Adv. NeurIPS."},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_38"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1561\/0600000105"},{"key":"ref24","article-title":"Places: An image database for deep scene understanding","author":"Zhou","year":"2016","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00444"},{"journal-title":"arXiv preprint","article-title":"GPT-4 technical report","year":"2023","key":"ref26"}],"event":{"name":"2024 15th International Conference on Information and Communication Technology Convergence (ICTC)","start":{"date-parts":[[2024,10,16]]},"location":"Jeju Island, Korea, Republic of","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 15th International Conference on Information and Communication Technology Convergence (ICTC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10826571\/10826594\/10826596.pdf?arnumber=10826596","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T17:51:14Z","timestamp":1746467474000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10826596\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,16]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/ictc62082.2024.10826596","relation":{},"subject":[],"published":{"date-parts":[[2024,10,16]]}}}