{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T20:24:47Z","timestamp":1787689487539,"version":"build-2784847793"},"publisher-location":"New York, NY, USA","reference-count":90,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770854.3785678","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:07:40Z","timestamp":1785499660000},"page":"2854-2865","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6069-5153","authenticated-orcid":false,"given":"Wenqian","family":"Ye","sequence":"first","affiliation":[{"name":"University of Virginia, Charlottesville, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6084-9133","authenticated-orcid":false,"given":"Bohan","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Virginia, Charlottesville, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1287-4931","authenticated-orcid":false,"given":"Guangtao","family":"Zheng","sequence":"additional","affiliation":[{"name":"University of Virginia, Charlottesville, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5741-6694","authenticated-orcid":false,"given":"Di","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Virginia, Charlottesville, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8739-5196","authenticated-orcid":false,"given":"Xu","family":"Cao","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Champaign, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3933-2574","authenticated-orcid":false,"given":"Yunsheng","family":"Ma","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, Indiana, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7578-7336","authenticated-orcid":false,"given":"Bolin","family":"Lai","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, Georgia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1793-5462","authenticated-orcid":false,"given":"James M.","family":"Rehg","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Champaign, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9723-3246","authenticated-orcid":false,"given":"Aidong","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Virginia, Charlottesville, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"e_1_3_2_2_1_1","first-page":"66","article-title":"Meaningfully debugging model mistakes using conceptual counterfactual explanations","author":"Abid Abubakar","year":"2022","unstructured":"Abubakar Abid, Mert Yuksekgonul, and James Zou. 2022. Meaningfully debugging model mistakes using conceptual counterfactual explanations. In ICML. PMLR, 66-88.","journal-title":"ICML. PMLR"},{"key":"e_1_3_2_2_2_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al., 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2403.04652"},{"key":"e_1_3_2_2_4_1","unstructured":"Anthropic. 2024. Claude 3 Family. https:\/\/www.anthropic.com\/news\/claude-3-family. Accessed: 2024-05-27."},{"key":"e_1_3_2_2_5_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang Binyuan Hui Luo Ji Mei Li Junyang Lin Runji Lin Dayiheng Liu Gao Liu Chengqiang Lu Keming Lu Jianxin Ma Rui Men Xingzhang Ren Xuancheng Ren Chuanqi Tan Sinan Tan Jianhong Tu Peng Wang Shijie Wang Wei Wang Shengguang Wu Benfeng Xu Jin Xu An Yang Hao Yang Jian Yang Shusheng Yang Yang Yao Bowen Yu Hongyi Yuan Zheng Yuan Jianwei Zhang Xingxuan Zhang Yichang Zhang Zhenru Zhang Chang Zhou Jingren Zhou Xiaohuan Zhou and Tianhang Zhu. 2023a. Qwen Technical Report. arXiv (Sept. 2023). doi:10.48550\/arXiv.2309.16609"},{"key":"e_1_3_2_2_6_1","volume-title":"Qwen-vl: A frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966","author":"Bai Jinze","year":"2023","unstructured":"Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023b. Qwen-vl: A frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)."},{"key":"e_1_3_2_2_7_1","volume-title":"arXiv preprint arXiv:2502.13923","author":"Bai Shuai","year":"2025","unstructured":"Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, Humen Zhong, Yuanzhi Zhu, Mingkun Yang, Zhaohai Li, Jianqiang Wan, Pengfei Wang, Wei Ding, Zheren Fu, Yiheng Xu, Jiabo Ye, Xi Zhang, Tianbao Xie, Zesen Cheng, Hang Zhang, Zhibo Yang, Haiyang Xu, and Junyang Lin. 2025. Qwen2.5-VL Technical Report. arXiv preprint arXiv:2502.13923 (2025)."},{"key":"e_1_3_2_2_8_1","volume-title":"Hallucination of multimodal large language models: A survey. arXiv preprint arXiv:2404.18930","author":"Bai Zechen","year":"2024","unstructured":"Zechen Bai, Pichao Wang, Tianjun Xiao, Tong He, Zongbo Han, Zheng Zhang, and Mike Zheng Shou. 2024. Hallucination of multimodal large language models: A survey. arXiv preprint arXiv:2404.18930 (2024)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00127"},{"key":"e_1_3_2_2_10_1","unstructured":"Andrei Barbu David Mayo Julian Alverio William Luo Christopher Wang Dan Gutfreund Josh Tenenbaum and Boris Katz. 2019. ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_2_11_1","volume-title":"Robustness of Structured Data Extraction from In-Plane Rotated Documents Using Multi-Modal Large Language Models (LLM). Journal of Artificial Intelligence Research","author":"Biswas Anjanava","year":"2024","unstructured":"Anjanava Biswas and Wrick Talukdar. 2024. Robustness of Structured Data Extraction from In-Plane Rotated Documents Using Multi-Modal Large Language Models (LLM). Journal of Artificial Intelligence Research (2024)."},{"key":"e_1_3_2_2_12_1","volume-title":"Visit-bench: A benchmark for vision-language instruction following inspired by real-world use. arXiv preprint arXiv:2308.06595","author":"Bitton Yonatan","year":"2023","unstructured":"Yonatan Bitton, Hritik Bansal, Jack Hessel, Rulin Shao, Wanrong Zhu, Anas Awadalla, Josh Gardner, Rohan Taori, and Ludwig Schimdt. 2023. Visit-bench: A benchmark for vision-language instruction following inspired by real-world use. arXiv preprint arXiv:2308.06595 (2023)."},{"key":"e_1_3_2_2_13_1","volume-title":"MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark. arXiv preprint arXiv:2402.04788","author":"Chen Dongping","year":"2024","unstructured":"Dongping Chen, Ruoxi Chen, Shilin Zhang, Yinuo Liu, Yaochen Wang, Huichi Zhou, Qihui Zhang, Pan Zhou, Yao Wan, and Lichao Sun. 2024. MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark. arXiv preprint arXiv:2402.04788 (2024)."},{"key":"e_1_3_2_2_14_1","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery Aakanksha","year":"2023","unstructured":"Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al., 2023. Palm: Scaling language modeling with pathways. Journal of Machine Learning Research, Vol. 24, 240 (2023), 1-113.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_15_1","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung Hyung Won","year":"2024","unstructured":"Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Yunxuan Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, et al., 2024. Scaling instruction-finetuned language models. Journal of Machine Learning Research, Vol. 25, 70 (2024), 1-53.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1418"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02325"},{"key":"e_1_3_2_2_18_1","volume-title":"Junqi Zhao, Weisheng Wang, Boyang Li, Pascale N Fung, and Steven Hoi.","author":"Dai Wenliang","year":"2024","unstructured":"Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale N Fung, and Steven Hoi. 2024. Instructblip: Towards general-purpose vision-language models with instruction tuning. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_2_19_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_2_20_1","volume-title":"Informativeness and invariance: Two perspectives on spurious correlations in natural language. arXiv preprint arXiv:2204.04487","author":"Eisenstein Jacob","year":"2022","unstructured":"Jacob Eisenstein. 2022. Informativeness and invariance: Two perspectives on spurious correlations in natural language. arXiv preprint arXiv:2204.04487 (2022)."},{"key":"e_1_3_2_2_21_1","volume-title":"Margret Keuper, and Janis Keuper.","author":"Gavrikov Paul","year":"2024","unstructured":"Paul Gavrikov, Jovita Lukasik, Steffen Jung, Robert Geirhos, Bianca Lamm, Muhammad Jehanzeb Mirza, Margret Keuper, and Janis Keuper. 2024. Are Vision Language Models Texture or Shape Biased and Can We Steer Them? arXiv preprint arXiv:2403.09193 (2024)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00257-z"},{"key":"e_1_3_2_2_23_1","volume-title":"ImageNet-trained CNNs are biased towards texture","author":"Geirhos Robert","unstructured":"Robert Geirhos, Patricia Rubisch, Claudio Michaelis, Matthias Bethge, Felix A. Wichmann, and Wieland Brendel. 2019. ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness.. In ICLR. https:\/\/openreview.net\/forum?id=Bygh9j09KX"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01916-5"},{"key":"e_1_3_2_2_25_1","volume-title":"The Instinctive Bias: Spurious Images lead to Hallucination in MLLMs. arXiv preprint arXiv:2402.03757","author":"Han Tianyang","year":"2024","unstructured":"Tianyang Han, Qing Lian, Rui Pan, Renjie Pi, Jipeng Zhang, Shizhe Diao, Yong Lin, and Tong Zhang. 2024. The Instinctive Bias: Spurious Images lead to Hallucination in MLLMs. arXiv preprint arXiv:2402.03757 (2024)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"e_1_3_2_2_28_1","volume-title":"Benchmarking neural network robustness to common corruptions and perturbations. arXiv preprint arXiv:1903.12261","author":"Hendrycks Dan","year":"2019","unstructured":"Dan Hendrycks and Thomas Dietterich. 2019. Benchmarking neural network robustness to common corruptions and perturbations. arXiv preprint arXiv:1903.12261 (2019)."},{"key":"e_1_3_2_2_29_1","first-page":"15262","article-title":"Natural adversarial examples","author":"Hendrycks Dan","year":"2021","unstructured":"Dan Hendrycks, Kevin Zhao, Steven Basart, Jacob Steinhardt, and Dawn Song. 2021b. Natural adversarial examples. In CVPR. 15262-15271.","journal-title":"CVPR."},{"key":"e_1_3_2_2_30_1","volume-title":"Seeing What's Not There: Spurious Correlation in Multimodal LLMs. arXiv preprint arXiv:2503.08884","author":"Hosseini Parsa","year":"2025","unstructured":"Parsa Hosseini, Sumit Nawathe, Mazda Moayeri, Sriram Balasubramanian, and Soheil Feizi. 2025. Seeing What's Not There: Spurious Correlation in Multimodal LLMs. arXiv preprint arXiv:2503.08884 (2025)."},{"key":"e_1_3_2_2_31_1","volume-title":"Opera: Alleviating hallucination in multi-modal large language models via over-trust penalty and retrospection-allocation. arXiv preprint arXiv:2311.17911","author":"Huang Qidong","year":"2023","unstructured":"Qidong Huang, Xiaoyi Dong, Pan Zhang, Bin Wang, Conghui He, Jiaqi Wang, Dahua Lin, Weiming Zhang, and Nenghai Yu. 2023b. Opera: Alleviating hallucination in multi-modal large language models via over-trust penalty and retrospection-allocation. arXiv preprint arXiv:2311.17911 (2023)."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3155"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","unstructured":"Albert Q. Jiang Alexandre Sablayrolles Arthur Mensch Chris Bamford Devendra Singh Chaplot Diego de las Casas Florian Bressand Gianna Lengyel Guillaume Lample Lucile Saulnier L\u00e9lio Renard Lavaud Marie-Anne Lachaux Pierre Stock Teven Le Scao Thibaut Lavril Thomas Wang Timoth\u00e9e Lacroix and William El Sayed. 2023. Mistral 7B. arXiv (Oct. 2023). doi:10.48550\/arXiv.2310.06825","DOI":"10.48550\/arXiv.2310.06825"},{"key":"e_1_3_2_2_35_1","unstructured":"Polina Kirichenko Pavel Izmailov and Andrew Gordon Wilson. 2023. Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations. In ICLR. https:\/\/openreview.net\/forum?id=Zb6c8A-Fghk"},{"key":"e_1_3_2_2_36_1","volume-title":"Wayne Xin Zhao, and Ji-Rong Wen","author":"Li Yifan","year":"2023","unstructured":"Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Wayne Xin Zhao, and Ji-Rong Wen. 2023. Evaluating object hallucination in large vision-language models. arXiv preprint arXiv:2305.10355 (2023)."},{"key":"e_1_3_2_2_37_1","volume-title":"Core Knowledge Deficits in Multi-Modal Language Models. arXiv preprint arXiv:2410.10855","author":"Li Yijiang","year":"2025","unstructured":"Yijiang Li, Qingying Gao, Tianwei Zhao, Bingyang Wang, Haoran Sun, Haiyun Lyu, Dezhi Luo, and Hokin Deng. 2025. Core Knowledge Deficits in Multi-Modal Language Models. arXiv preprint arXiv:2410.10855 (2025)."},{"key":"e_1_3_2_2_38_1","first-page":"6781","article-title":"Just train twice: Improving group robustness without training group information","author":"Liu Evan Z","year":"2021","unstructured":"Evan Z Liu, Behzad Haghgoo, Annie S Chen, Aditi Raghunathan, Pang Wei Koh, Shiori Sagawa, Percy Liang, and Chelsea Finn. 2021. Just train twice: Improving group robustness without training group information. In ICML. PMLR, 6781-6792.","journal-title":"ICML. PMLR"},{"key":"e_1_3_2_2_39_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2024)."},{"key":"e_1_3_2_2_40_1","volume-title":"Mmbench: Is your multi-modal model an all-around player? arXiv preprint arXiv:2307.06281","author":"Liu Yuan","year":"2023","unstructured":"Yuan Liu, Haodong Duan, Yuanhan Zhang, Bo Li, Songyang Zhang, Wangbo Zhao, Yike Yuan, Jiaqi Wang, Conghui He, Ziwei Liu, et al., 2023. Mmbench: Is your multi-modal model an all-around player? arXiv preprint arXiv:2307.06281 (2023)."},{"key":"e_1_3_2_2_41_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Lu Zeyu","year":"2024","unstructured":"Zeyu Lu, Di Huang, Lei Bai, Jingjing Qu, Chengyue Wu, Xihui Liu, and Wanli Ouyang. 2024. Seeing is not always believing: Benchmarking human and model perception of ai-generated images. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01119"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"crossref","unstructured":"Brandon McKinzie Zhe Gan Jean-Philippe Fauconnier Sam Dodge Bowen Zhang Philipp Dufter Dhruti Shah Xianzhi Du Futang Peng Floris Weers et al. 2024. Mm1: Methods analysis & insights from multimodal llm pre-training. arXiv preprint arXiv:2403.09611 (2024).","DOI":"10.1007\/978-3-031-73397-0_18"},{"key":"e_1_3_2_2_44_1","volume-title":"Selection Bias Induced Spurious Correlations in Large Language Models. In ICML 2022: Workshop on Spurious Correlations, Invariance and Stability. https:\/\/openreview.net\/forum?id=8nnaDv9dUli","author":"McMilin Emily","year":"2022","unstructured":"Emily McMilin. 2022. Selection Bias Induced Spurious Correlations in Large Language Models. In ICML 2022: Workshop on Spurious Correlations, Invariance and Stability. https:\/\/openreview.net\/forum?id=8nnaDv9dUli"},{"key":"e_1_3_2_2_45_1","unstructured":"AI Meta. 2024a. Introducing Llama 3.1: Our most capable models to date. https:\/\/ai.meta.com\/blog\/meta-llama-3-1\/"},{"key":"e_1_3_2_2_46_1","unstructured":"AI Meta. 2024b. Llama 3.2: Revolutionizing edge AI and vision with open customizable models. https:\/\/ai.meta.com\/blog\/llama-3-2-connect-2024-vision-edge-mobile-devices\/"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i9.21244"},{"key":"e_1_3_2_2_48_1","unstructured":"Junhyun Nam Jaehyung Kim Jaeho Lee and Jinwoo Shin. 2022. Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimation. In ICLR. https:\/\/openreview.net\/forum?id=_F9xpOrqyX9"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics12010040"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1609\/hcomp.v6i1.13337"},{"key":"e_1_3_2_2_51_1","unstructured":"Maxime Oquab Timoth\u00e9e Darcet Th\u00e9o Moutakanni Huy Vo Marc Szafraniec Vasil Khalidov Pierre Fernandez Daniel Haziza Francisco Massa Alaaeldin El-Nouby et al. 2023. Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)."},{"key":"e_1_3_2_2_52_1","volume-title":"Marco Tulio Ribeiro, and Ameet Talwalkar","author":"Plumb Gregory","year":"2022","unstructured":"Gregory Plumb, Marco Tulio Ribeiro, and Ameet Talwalkar. 2022. Finding and Fixing Spurious Patterns with Explanations. Transactions on Machine Learning Research (2022). https:\/\/openreview.net\/forum?id=whJPugmP5I Expert Certification."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1094"},{"key":"e_1_3_2_2_54_1","volume-title":"Semanticadv: Generating adversarial examples via attribute-conditioned image editing. In Computer Vision-ECCV 2020: 16th European Conference","author":"Qiu Haonan","year":"2020","unstructured":"Haonan Qiu, Chaowei Xiao, Lei Yang, Xinchen Yan, Honglak Lee, and Bo Li. 2020. Semanticadv: Generating adversarial examples via attribute-conditioned image editing. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XIV 16. Springer, 19-37."},{"key":"e_1_3_2_2_55_1","volume-title":"International conference on machine learning. PMLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748-8763."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"e_1_3_2_2_57_1","volume-title":"Tatsunori B Hashimoto, and Percy Liang.","author":"Sagawa Shiori","year":"2019","unstructured":"Shiori Sagawa, Pang Wei Koh, Tatsunori B Hashimoto, and Percy Liang. 2019. Distributionally Robust Neural Networks. In ICLR."},{"key":"e_1_3_2_2_58_1","first-page":"8346","article-title":"An investigation of why overparameterization exacerbates spurious correlations","author":"Sagawa Shiori","year":"2020","unstructured":"Shiori Sagawa, Aditi Raghunathan, Pang Wei Koh, and Percy Liang. 2020. An investigation of why overparameterization exacerbates spurious correlations. In ICML. PMLR, 8346-8356.","journal-title":"ICML. PMLR"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"crossref","unstructured":"Amanpreet Singh Vivek Natarajan Meet Shah Yu Jiang Xinlei Chen Dhruv Batra Devi Parikh and Marcus Rohrbach. 2019. Towards vqa models that can read. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 8317-8326.","DOI":"10.1109\/CVPR.2019.00851"},{"key":"e_1_3_2_2_61_1","volume-title":"Zoom is what you need: An empirical study of the power of zoom and spatial biases in image classification. arXiv preprint arXiv:2304.05538","author":"Taesiri Mohammad Reza","year":"2023","unstructured":"Mohammad Reza Taesiri, Giang Nguyen, Sarra Habchi, Cor-Paul Bezemer, and Anh Nguyen. 2023. Zoom is what you need: An empirical study of the power of zoom and spatial biases in image classification. arXiv preprint arXiv:2304.05538 (2023)."},{"key":"e_1_3_2_2_62_1","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Yonghui Wu Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M Dai Anja Hauth et al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"e_1_3_2_2_63_1","volume-title":"Eyes wide shut? exploring the visual shortcomings of multimodal llms. arXiv preprint arXiv:2401.06209","author":"Tong Shengbang","year":"2024","unstructured":"Shengbang Tong, Zhuang Liu, Yuexiang Zhai, Yi Ma, Yann LeCun, and Saining Xie. 2024. Eyes wide shut? exploring the visual shortcomings of multimodal llms. arXiv preprint arXiv:2401.06209 (2024)."},{"key":"e_1_3_2_2_64_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al., 2023a. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Dan Bikel Lukas Blecher Cristian Canton Ferrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel Kloumann Artem Korenev Punit Singh Koura Marie-Anne Lachaux Thibaut Lavril Jenya Lee Diana Liskovich Yinghai Lu Yuning Mao Xavier Martinet Todor Mihaylov Pushkar Mishra Igor Molybog Yixin Nie Andrew Poulton Jeremy Reizenstein Rashi Rungta Kalyan Saladi Alan Schelten Ruan Silva Eric Michael Smith Ranjan Subramanian Xiaoqing Ellen Tan Binh Tang Ross Taylor Adina Williams Jian Xiang Kuan Puxin Xu Zheng Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aurelien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. 2023b. Llama 2: Open Foundation and Fine-Tuned Chat Models. arXiv (2023). doi:10.48550\/arXiv.2307.09288","DOI":"10.48550\/arXiv.2307.09288"},{"key":"e_1_3_2_2_66_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Wang Haohan","year":"2019","unstructured":"Haohan Wang, Songwei Ge, Zachary Lipton, and Eric P Xing. 2019. Learning robust global representations by penalizing local predictive power. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.130"},{"key":"e_1_3_2_2_68_1","volume-title":"arXiv preprint arXiv:2402.14899","author":"Wang Zefeng","year":"2024","unstructured":"Zefeng Wang, Zhen Han, Shuo Chen, Fan Xue, Zifeng Ding, Xun Xiao, Volker Tresp, Philip Torr, and Jindong Gu. 2024. Stop Reasoning! When Multimodal LLMs with Chain-of-Thought Reasoning Meets Adversarial Images. arXiv preprint arXiv:2402.14899 (2024)."},{"key":"e_1_3_2_2_69_1","volume-title":"Brian Lester, Nan Du, Andrew M Dai, and Quoc V Le.","author":"Wei Jason","year":"2021","unstructured":"Jason Wei, Maarten Bosma, Vincent Y Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M Dai, and Quoc V Le. 2021. Finetuned language models are zero-shot learners. arXiv preprint arXiv:2109.01652 (2021)."},{"key":"e_1_3_2_2_70_1","volume-title":"Guided Visual Search as a Core Mechanism in Multimodal LLMs. arXiv preprint arXiv:2312.14135","author":"Wu Penghao","year":"2023","unstructured":"Penghao Wu and Saining Xie. 2023. V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs. arXiv preprint arXiv:2312.14135 (2023)."},{"key":"e_1_3_2_2_71_1","volume-title":"Discover and Cure: Concept-aware Mitigation of Spurious Correlation. arXiv preprint arXiv:2305.00650","author":"Wu Shirley","year":"2023","unstructured":"Shirley Wu, Mert Yuksekgonul, Linjun Zhang, and James Zou. 2023. Discover and Cure: Concept-aware Mitigation of Spurious Correlation. arXiv preprint arXiv:2305.00650 (2023)."},{"key":"e_1_3_2_2_72_1","unstructured":"Kai Xiao Logan Engstrom Andrew Ilyas and Aleksander Madry. 2021. Noise or Signal: The Role of Image Backgrounds in Object Recognition. In ICLR."},{"key":"e_1_3_2_2_73_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Xue Yihao","year":"2024","unstructured":"Yihao Xue, Siddharth Joshi, Dang Nguyen, and Baharan Mirzasoleiman. 2024. Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_2_74_1","volume-title":"International Conference on Machine Learning. PMLR, 39365-39379","author":"Yang Yu","year":"2023","unstructured":"Yu Yang, Besmira Nushi, Hamid Palangi, and Baharan Mirzasoleiman. 2023a. Mitigating spurious correlations in multi-modal models during fine-tuning. In International Conference on Machine Learning. PMLR, 39365-39379."},{"key":"e_1_3_2_2_75_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning. 39584-39622","author":"Yang Yuzhe","year":"2023","unstructured":"Yuzhe Yang, Haoran Zhang, Dina Katabi, and Marzyeh Ghassemi. 2023b. Change is hard: a closer look at subpopulation shift. In Proceedings of the 40th International Conference on Machine Learning. 39584-39622."},{"key":"e_1_3_2_2_76_1","volume-title":"SAGE: Spuriousness-Aware Guided Prompt Exploration for Mitigating Multimodal Bias. AAAI Conference on Artificial Intelligence (AAAI)","author":"Ye Wenqian","year":"2026","unstructured":"Wenqian Ye, Di Wang, Guangtao Zheng, Bohan Liu, and Aidong Zhang. 2026. SAGE: Spuriousness-Aware Guided Prompt Exploration for Mitigating Multimodal Bias. AAAI Conference on Artificial Intelligence (AAAI) (2026)."},{"key":"e_1_3_2_2_77_1","volume-title":"Spurious Correlations in Machine Learning: A Survey. arXiv preprint arXiv:2402.12715","author":"Ye Wenqian","year":"2024","unstructured":"Wenqian Ye, Guangtao Zheng, Xu Cao, Yunsheng Ma, and Aidong Zhang. 2024. Spurious Correlations in Machine Learning: A Survey. arXiv preprint arXiv:2402.12715 (2024)."},{"key":"e_1_3_2_2_78_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Yin Zhenfei","year":"2024","unstructured":"Zhenfei Yin, Jiong Wang, Jianjian Cao, Zhelun Shi, Dingning Liu, Mukai Li, Xiaoshui Huang, Zhiyong Wang, Lu Sheng, Lei Bai, et al., 2024. Lamm: Language-assisted multi-modal instruction-tuning dataset, framework, and benchmark. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_2_79_1","volume-title":"Spurious Feature Diversification Improves Out-of-distribution Generalization. In The Twelfth International Conference on Learning Representations.","author":"Yong Lin","year":"2023","unstructured":"Lin Yong, Lu Tan, Hao Yifan, Ho Nam Wong, Hanze Dong, Weizhong Zhang, Yujiu Yang, and Tong Zhang. 2023. Spurious Feature Diversification Improves Out-of-distribution Generalization. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_2_80_1","volume-title":"Mm-vet: Evaluating large multimodal models for integrated capabilities. arXiv preprint arXiv:2308.02490","author":"Yu Weihao","year":"2023","unstructured":"Weihao Yu, Zhengyuan Yang, Linjie Li, Jianfeng Wang, Kevin Lin, Zicheng Liu, Xinchao Wang, and Lijuan Wang. 2023. Mm-vet: Evaluating large multimodal models for integrated capabilities. arXiv preprint arXiv:2308.02490 (2023)."},{"key":"e_1_3_2_2_81_1","volume-title":"Investigating the Catastrophic Forgetting in Multimodal Large Language Model Fine-Tuning. In Conference on Parsimony and Learning. PMLR, 202-227","author":"Zhai Yuexiang","year":"2024","unstructured":"Yuexiang Zhai, Shengbang Tong, Xiao Li, Mu Cai, Qing Qu, Yong Jae Lee, and Yi Ma. 2024. Investigating the Catastrophic Forgetting in Multimodal Large Language Model Fine-Tuning. In Conference on Parsimony and Learning. PMLR, 202-227."},{"key":"e_1_3_2_2_82_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_2"},{"key":"e_1_3_2_2_83_1","volume-title":"Manifold: A model-agnostic framework for interpretation and diagnosis of machine learning models","author":"Zhang Jiawei","year":"2018","unstructured":"Jiawei Zhang, Yang Wang, Piero Molino, Lezhi Li, and David S Ebert. 2018. Manifold: A model-agnostic framework for interpretation and diagnosis of machine learning models. IEEE transactions on visualization and computer graphics, Vol. 25, 1 (2018), 364-373."},{"key":"e_1_3_2_2_84_1","volume-title":"Xi Victoria Lin, et al","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al., 2022. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)."},{"key":"e_1_3_2_2_85_1","volume-title":"European Conference on Computer Vision. Springer, 346-364","author":"Zheng Guangtao","year":"2024","unstructured":"Guangtao Zheng, Wenqian Ye, and Aidong Zhang. 2024a. Benchmarking spurious bias in few-shot image classifiers. In European Conference on Computer Vision. Springer, 346-364."},{"key":"e_1_3_2_2_86_1","volume-title":"Learning Robust Classifiers with Self-Guided Spurious Correlation Mitigation. In The 33rd International Joint Conference on Artificial Intelligence.","author":"Zheng Guangtao","year":"2024","unstructured":"Guangtao Zheng, Wenqian Ye, and Aidong Zhang. 2024b. Learning Robust Classifiers with Self-Guided Spurious Correlation Mitigation. In The 33rd International Joint Conference on Artificial Intelligence."},{"key":"e_1_3_2_2_87_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3672006"},{"key":"e_1_3_2_2_88_1","doi-asserted-by":"publisher","unstructured":"Lianmin Zheng Wei-Lin Chiang Ying Sheng Siyuan Zhuang Zhanghao Wu Yonghao Zhuang Zi Lin Zhuohan Li Dacheng Li Eric P. Xing Hao Zhang Joseph E. Gonzalez and Ion Stoica. 2023. Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena. In NeurIPS Datasets and Benchmarks Track. doi:10.48550\/arXiv.2306.05685","DOI":"10.48550\/arXiv.2306.05685"},{"key":"e_1_3_2_2_89_1","volume-title":"Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models. arXiv preprint arXiv:2402.12048","author":"Zhu Didi","year":"2024","unstructured":"Didi Zhu, Zhongyi Sun, Zexi Li, Tao Shen, Ke Yan, Shouhong Ding, Kun Kuang, and Chao Wu. 2024. Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models. arXiv preprint arXiv:2402.12048 (2024)."},{"key":"e_1_3_2_2_90_1","unstructured":"Jinguo Zhu Weiyun Wang Zhe Chen Zhaoyang Liu Shenglong Ye Lixin Gu Hao Tian Yuchen Duan Weijie Su Jie Shao Zhangwei Gao Erfei Cui Xuehui Wang Yue Cao Yangzhou Liu Xingguang Wei Hongjie Zhang Haomin Wang Weiye Xu Hao Li Jiahao Wang Nianchen Deng Songze Li Yinan He Tan Jiang Jiapeng Luo Yi Wang Conghui He Botian Shi Xingcheng Zhang Wenqi Shao Junjun He Yingtong Xiong Wenwen Qu Peng Sun Penglong Jiao Han Lv Lijun Wu Kaipeng Zhang Huipeng Deng Jiaye Ge Kai Chen Limin Wang Min Dou Lewei Lu Xizhou Zhu Tong Lu Dahua Lin Yu Qiao Jifeng Dai and Wenhai Wang. 2025. InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models. arXiv:2504.10479"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770854.3785678","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T20:13:16Z","timestamp":1787688796000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770854.3785678"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":90,"alternative-id":["10.1145\/3770854.3785678","10.1145\/3770854"],"URL":"https:\/\/doi.org\/10.1145\/3770854.3785678","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]},"assertion":[{"value":"2026-04-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}