{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T00:59:52Z","timestamp":1755219592959,"version":"3.43.0"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T00:00:00Z","timestamp":1748217600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T00:00:00Z","timestamp":1748217600000},"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":[[2025,5,26]]},"DOI":"10.1109\/fg61629.2025.11099161","type":"proceedings-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T17:55:00Z","timestamp":1754502900000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["Investigating Social Biases in Multimodal LLMs"],"prefix":"10.1109","author":[{"given":"Malsha V.","family":"Perera","sequence":"first","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kartik","family":"Narayan","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vishal M.","family":"Patel","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","volume-title":"arXiv preprint arXiv:2404.14219","author":"Abdin","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462624"},{"key":"ref3","article-title":"Qwen technical report","volume-title":"arXiv preprint arXiv:2309.16609","author":"Bai","year":"2023"},{"key":"ref4","article-title":"Paligemma: A versatile 3b vlm for transfer","author":"Beyer","year":"2024","journal-title":"arXiv preprint arXiv:2407.07726"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00283"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00106"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671458"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3370437"},{"volume-title":"\u201cthe large language model (llm) bias evaluation (age bias)\u201d-dikwp research group international standard evaluation","year":"2024","author":"Duan","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00524"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aies.v7i1.31657"},{"volume-title":"Cogvlm2: Visual language models for image and video understanding","year":"2024","author":"Hong","key":"ref14"},{"key":"ref15","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint arXiv:2410.21276"},{"key":"ref16","article-title":"Mantis: Interleaved multi-image instruction tuning","author":"Jiang","year":"2024","journal-title":"arXiv preprint arXiv:2405.01483"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00159"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"volume-title":"Obelics: An open web-scale filtered dataset of interleaved image-text documents","year":"2023","author":"Lauren\u00e7on","key":"ref19"},{"volume-title":"What matters when building vision-language models?","year":"2024","author":"Lauren\u00e7on","key":"ref20"},{"key":"ref21","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv:2408.03326"},{"key":"ref22","article-title":"Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv:2407.07895"},{"key":"ref23","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"In International conference on machine learning","author":"Li"},{"volume-title":"A survey on fairness in large language models","year":"2024","author":"Li","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"volume-title":"Investigating bias in llmbased bias detection: Disparities between llms and human perception","year":"2024","author":"Lin","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102795"},{"key":"ref29","first-page":"36","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref30","article-title":"Sora: A review on background, technology, limitations, and opportunities of large vision models","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv:2402.17177"},{"article-title":"Stable bias: evaluating societal representations in diffusion models","volume-title":"In Proceedings of the 37th International Conference on Neural Information Processing Systems, NIPS \u201923","author":"Luccioni","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.416"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2025.3561475"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3600211.3604711"},{"volume-title":"Facexbench: Evaluating multimodal llms on face understanding","year":"2025","author":"Narayan","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00637"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2024.3525037"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-37731-0_40"},{"key":"ref39","article-title":"Eagle: Exploring the design space for multimodal llms with mixture of encoders","author":"Shi","year":"2024","journal-title":"arXiv:2408.15998"},{"key":"ref40","article-title":"Chameleon: Mixed-modal early-fusion foundation models","author":"Team","year":"2024","journal-title":"arXiv preprint arXiv:2405.09818"},{"volume-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","year":"2024","author":"Team","key":"ref41"},{"key":"ref42","article-title":"Cambrian-1: A fully open, vision-centric exploration of multimodal llms","author":"Tong","year":"2024","journal-title":"arXiv preprint arXiv:2406.16860"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3651029"},{"key":"ref44","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv:2409.12191"},{"key":"ref45","article-title":"Cogvlm: Visual expert for pretrained language models","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2311.03079"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681589"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.283"},{"key":"ref48","article-title":"Minicpmv: A gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arXiv preprint 2408.01800"},{"key":"ref49","article-title":"mplug-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023","journal-title":"arXiv preprint arXiv:2304.14178"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00367"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.463"},{"key":"ref52","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint arXiv:2304.10592"}],"event":{"name":"2025 IEEE 19th International Conference on Automatic Face and Gesture Recognition (FG)","start":{"date-parts":[[2025,5,26]]},"location":"Tampa\/Clearwater, FL, USA","end":{"date-parts":[[2025,5,30]]}},"container-title":["2025 IEEE 19th International Conference on Automatic Face and Gesture Recognition (FG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11099084\/11099070\/11099161.pdf?arnumber=11099161","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T05:02:25Z","timestamp":1754542945000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11099161\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,26]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/fg61629.2025.11099161","relation":{},"subject":[],"published":{"date-parts":[[2025,5,26]]}}}