{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:06:25Z","timestamp":1777889185564,"version":"3.51.4"},"reference-count":75,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00170","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1740-1750","source":"Crossref","is-referenced-by-count":0,"title":["Social Debiasing for Fair Multi-Modal LLMs"],"prefix":"10.1109","author":[{"given":"Harry","family":"Cheng","sequence":"first","affiliation":[{"name":"Shandong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yangyang","family":"Guo","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingpei","family":"Guo","sequence":"additional","affiliation":[{"name":"University of Warwick"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Yang","sequence":"additional","affiliation":[{"name":"Ant Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tian","family":"Gan","sequence":"additional","affiliation":[{"name":"Shandong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weili","family":"Guan","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Flamingo: a visual language model for few-shot learning","volume-title":"NeurIPS","author":"Alayrac","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11009-3_34"},{"key":"ref3","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"CoRR, abs\/2308.12966"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.aacl-main.61"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/e23091165"},{"key":"ref6","article-title":"Multimodal datasets: misogyny, pornography, and malignant stereotypes","author":"Birhane","year":"2021","journal-title":"CoRR, abs\/2110.01963"},{"key":"ref7","first-page":"4349","article-title":"Man is to computer programmer as woman is to homemaker? debiasing word embeddings","volume-title":"NeurIPS","author":"Bolukbasi","year":"2016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00453"},{"key":"ref9","first-page":"1","article-title":"Language models are few-shot learners","volume-title":"NeurIPS","author":"Brown","year":"2020"},{"key":"ref10","first-page":"1","article-title":"Pali: A jointlyscaled multilingual language-image model","volume-title":"ICLR","author":"Chen","year":"2023"},{"key":"ref11","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality"},{"key":"ref12","first-page":"1","article-title":"Fair mixup: Fairness via interpolation","volume-title":"ICLR","author":"Chuang","year":"2021"},{"key":"ref13","article-title":"Debiasing vision-language models via biased prompts","author":"Chuang","year":"2023","journal-title":"CoRR, abs\/2302.00070"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref15","first-page":"1","article-title":"Fairerclip: Debiasing clip\u2019s zero-shot predictions using functions in rkhss","volume-title":"ICLR","author":"Dehdashtian","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ssresearch.2012.04.006"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-long.41"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00524"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1720347115"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330691"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3565266"},{"key":"ref24","first-page":"1","article-title":"Visogender: A dataset for benchmarking gender bias in image-text pronoun resolution","volume-title":"NeurIPS","author":"Hall","year":"2023"},{"key":"ref25","article-title":"Efficient multimodal learning from data-centric perspective","author":"He","year":"2024","journal-title":"CoRR, abs\/2402.11530"},{"key":"ref26","first-page":"1","article-title":"Prompt-to-prompt image editing with cross-attention control","volume-title":"ICLR","author":"Hertz","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01138"},{"key":"ref28","first-page":"1","article-title":"Language is not all you need: Aligning perception with language models","volume-title":"NeurIPS","author":"Huang","year":"2023"},{"key":"ref29","article-title":"Specify and edit: Overcoming ambiguity in textbased image editing","author":"Iakovleva","year":"2024","journal-title":"CoRR, abs\/2407.20232"},{"key":"ref30","author":"Ilharco","year":"2021","journal-title":"Openclip"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.126"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.53"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00159"},{"key":"ref34","first-page":"1","article-title":"Cococounterfactuals: Automatically constructed counterfactual examples for image-text pairs","volume-title":"NeurIPS","author":"Le","year":"2024"},{"key":"ref35","first-page":"12888","article-title":"BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"ICML","author":"Li","year":"2022"},{"key":"ref36","first-page":"19730","article-title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"ICML","author":"Li","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref39","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210003"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3573023"},{"key":"ref42","author":"Lu","year":"2024","journal-title":"Pinco: Position-induced consistent adapter for diffusion transformer in foreground-conditioned inpainting"},{"key":"ref43","author":"Lu","year":"2024","journal-title":"Deepseek-vl: Towards real-world visionlanguage understanding"},{"key":"ref44","first-page":"3381","article-title":"Learning adversarially fair and transferable representations","volume-title":"ICML","author":"Madras","year":"2018"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1062"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1111\/cdep.12424"},{"key":"ref47","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","author":"Ouyang","year":"2022","journal-title":"NeurIPS"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1177\/0190272513506229"},{"key":"ref49","author":"Podell","year":"2023","journal-title":"SDXL: improving latent diffusion models for high-resolution image synthesis"},{"key":"ref50","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref51","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"Raffel","year":"2020","journal-title":"JMLR"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00918"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/iccvw69036.2025.00651"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2019.2945519"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00659"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_44"},{"key":"ref57","first-page":"1","article-title":"VL-BERT: pre-training of generic visual-linguistic representations","volume-title":"ICLR","author":"Su","year":"2020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01709"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s12187-021-09897-y"},{"key":"ref60","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"key":"ref61","author":"Veldanda","year":"2023","journal-title":"Are emily and greg still more employable than lakisha and jamal? investigating algorithmic hiring bias in the era of chatgpt"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1080\/00224545.1957.9714322"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00366"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.22"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.151"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00934"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.1251"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02556-7"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7502-7_79-1"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3312302"},{"key":"ref71","first-page":"59310","article-title":"Multi-factor adaptive vision selection for egocentric video question answering","volume-title":"ICML","author":"Zhang","year":"2024"},{"key":"ref72","author":"Zhang","year":"2024","journal-title":"Vlbiasbench: A comprehensive benchmark for evaluating bias in large visionlanguage model"},{"key":"ref73","first-page":"21682","article-title":"Contrastive adapters for foundation model group robustness","author":"Zhang","year":"2022","journal-title":"NeurIPS"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.actpsy.2022.103754"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.aacl-main.40"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446072.pdf?arnumber=11446072","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:09:31Z","timestamp":1777612171000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446072\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00170","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}