{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,19]],"date-time":"2026-09-19T17:26:45Z","timestamp":1789838805470,"version":"4.0.1"},"publisher-location":"New York, NY, USA","reference-count":66,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["No. 2021YFF0901003"],"award-info":[{"award-number":["No. 2021YFF0901003"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657729","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"218-228","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["COMI: COrrect and MItigate Shortcut Learning Behavior in Deep Neural Networks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5786-2424","authenticated-orcid":false,"given":"Lili","family":"Zhao","sequence":"first","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6956-5550","authenticated-orcid":false,"given":"Qi","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China & Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5980-6098","authenticated-orcid":false,"given":"Linan","family":"Yue","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4700-2612","authenticated-orcid":false,"given":"Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2166-4386","authenticated-orcid":false,"given":"Liyi","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5751-1252","authenticated-orcid":false,"given":"Ruijun","family":"Sun","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6161-0242","authenticated-orcid":false,"given":"Chao","family":"Song","sequence":"additional","affiliation":[{"name":"OPPO, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_28"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"e_1_3_2_1_3_1","volume-title":"Explainable AI: To Reveal the Logic of Black-Box Models. New Generation Computing","author":"Urvashi Bansal Chinu","year":"2023","unstructured":"Chinu and Urvashi Bansal. 2023. Explainable AI: To Reveal the Logic of Black-Box Models. New Generation Computing (2023), 1--35."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1418"},{"key":"e_1_3_2_1_5_1","volume-title":"International Conference on Machine Learning, ICML. 2189--2200","author":"Creager Elliot","year":"2021","unstructured":"Elliot Creager, J\u00f6rn-Henrik Jacobsen, and Richard Zemel. 2021. Environment inference for invariant learning. In International Conference on Machine Learning, ICML. 2189--2200."},{"key":"e_1_3_2_1_6_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers). 4171--4186."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3596490"},{"key":"e_1_3_2_1_8_1","unstructured":"Mengnan Du Varun Manjunatha Rajiv Jain Ruchi Deshpande Franck Dernoncourt Jiuxiang Gu Tong Sun and Xia Hu. 2021. Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU models. In NAACL: Human Language Technologies. 915--929."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00257-z"},{"key":"e_1_3_2_1_10_1","volume-title":"International Conference on Learning Representations, ICLR.","author":"Geirhos Robert","year":"2018","unstructured":"Robert Geirhos, Patricia Rubisch, Claudio Michaelis, Matthias Bethge, Felix A Wichmann, and Wieland Brendel. 2018. ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. In International Conference on Learning Representations, ICLR."},{"key":"e_1_3_2_1_11_1","volume-title":"International conference on machine learning, ICML. 1321--1330","author":"Guo Chuan","year":"2017","unstructured":"Chuan Guo, Geoff Pleiss, Yu Sun, and Kilian Q Weinberger. 2017. On calibration of modern neural networks. In International conference on machine learning, ICML. 1321--1330."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-6115"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"e_1_3_2_1_15_1","volume-title":"International Conference on Learning Representations, ICLR.","author":"Hendrycks Dan","year":"2019","unstructured":"Dan Hendrycks, Norman Mu, Ekin Dogus Cubuk, Barret Zoph, Justin Gilmer, and Balaji Lakshminarayanan. 2019. AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty. In International Conference on Learning Representations, ICLR."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5964\/jnc.10085"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00729-y"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6311"},{"key":"e_1_3_2_1_19_1","volume-title":"The Eleventh International Conference on Learning Representations, ICLR.","author":"Kirichenko Polina","year":"2023","unstructured":"Polina Kirichenko, Pavel Izmailov, and Andrew Gordon Wilson. 2023. Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations. In The Eleventh International Conference on Learning Representations, ICLR."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.84"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Yuxuan Lai Chen Zhang Yansong Feng Quzhe Huang and Dongyan Zhao. 2021. Why Machine Reading Comprehension Models Learn Shortcuts?. In Findings of the Association for Computational Linguistics: ACL-IJCNLP. 989--1002.","DOI":"10.18653\/v1\/2021.findings-acl.85"},{"key":"e_1_3_2_1_22_1","first-page":"8935","article-title":"Residual distillation: Towards portable deep neural networks without shortcuts","volume":"33","author":"Li Guilin","year":"2020","unstructured":"Guilin Li, Junlei Zhang, Yunhe Wang, Chuanjian Liu, Matthias Tan, Yunfeng Lin, Wei Zhang, Jiashi Feng, and Tong Zhang. 2020. Residual distillation: Towards portable deep neural networks without shortcuts. Advances in Neural Information Processing Systems, Vol. 33 (2020), 8935--8946.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01922"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_16"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462981"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462943"},{"key":"e_1_3_2_1_27_1","volume-title":"International Conference on Machine Learning, ICML. 6781--6792","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 International Conference on Machine Learning, ICML. 6781--6792."},{"key":"e_1_3_2_1_28_1","volume-title":"Decoupled Weight Decay Regularization. In International Conference on Learning Representations, ICLR.","author":"Loshchilov Ilya","year":"2018","unstructured":"Ilya Loshchilov and Frank Hutter. 2018. Decoupled Weight Decay Regularization. In International Conference on Learning Representations, ICLR."},{"key":"e_1_3_2_1_29_1","first-page":"13073","article-title":"Rectifying the shortcut learning of background for few-shot learning","volume":"34","author":"Luo Xu","year":"2021","unstructured":"Xu Luo, Longhui Wei, Liangjian Wen, Jinrong Yang, Lingxi Xie, Zenglin Xu, and Qi Tian. 2021. Rectifying the shortcut learning of background for few-shot learning. Advances in Neural Information Processing Systems, Vol. 34 (2021), 13073--13085.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1334"},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of the 27th International Conference on Computational Linguistics. 2340--2353","author":"Naik Aakanksha","year":"2018","unstructured":"Aakanksha Naik, Abhilasha Ravichander, Norman Sadeh, Carolyn Rose, and Graham Neubig. 2018. Stress Test Evaluation for Natural Language Inference. In Proceedings of the 27th International Conference on Computational Linguistics. 2340--2353."},{"key":"e_1_3_2_1_32_1","first-page":"20673","article-title":"Learning from failure: De-biasing classifier from biased classifier","volume":"33","author":"Nam Junhyun","year":"2020","unstructured":"Junhyun Nam, Hyuntak Cha, Sungsoo Ahn, Jaeho Lee, and Jinwoo Shin. 2020. Learning from failure: De-biasing classifier from biased classifier. Advances in Neural Information Processing Systems, Vol. 33 (2020), 20673--20684.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1459"},{"key":"e_1_3_2_1_34_1","first-page":"1256","article-title":"Gradient starvation: A learning proclivity in neural networks","volume":"34","author":"Pezeshki Mohammad","year":"2021","unstructured":"Mohammad Pezeshki, Oumar Kaba, Yoshua Bengio, Aaron C Courville, Doina Precup, and Guillaume Lajoie. 2021. Gradient starvation: A learning proclivity in neural networks. Advances in Neural Information Processing Systems, Vol. 34 (2021), 1256--1272.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.374"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Yuqi Ren and Deyi Xiong. 2023. HuaSLIM: Human Attention Motivated Shortcut Learning Identification and Mitigation for Large Language models. In Findings of the Association for Computational Linguistics: ACL-IJCNLP. 12350--12365.","DOI":"10.18653\/v1\/2023.findings-acl.781"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_3_2_1_38_1","volume-title":"A stochastic approximation method. The annals of mathematical statistics","author":"Robbins Herbert","year":"1951","unstructured":"Herbert Robbins and Sutton Monro. 1951. A stochastic approximation method. The annals of mathematical statistics (1951), 400--407."},{"key":"e_1_3_2_1_39_1","volume-title":"Can contrastive learning avoid shortcut solutions? Advances in neural information processing systems","author":"Robinson Joshua","year":"2021","unstructured":"Joshua Robinson, Li Sun, Ke Yu, Kayhan Batmanghelich, Stefanie Jegelka, and Suvrit Sra. 2021. Can contrastive learning avoid shortcut solutions? Advances in neural information processing systems, Vol. 34 (2021), 4974--4986."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Olga Russakovsky Jia Deng Hao Su Jonathan Krause Sanjeev Satheesh Sean Ma Zhiheng Huang Andrej Karpathy Aditya Khosla Michael Bernstein et al. 2015. Imagenet large scale visual recognition challenge. International journal of computer vision Vol. 115 (2015) 211--252.","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_41_1","unstructured":"Chaitanya K Ryali David J Schwab and Ari S Morcos. 2021. Characterizing and improving the robustness of self-supervised learning through background augmentations. (2021)."},{"key":"e_1_3_2_1_42_1","volume-title":"Distributionally Robust Neural Networks. In International Conference on Learning Representations, ICLR.","author":"Sagawa Shiori","year":"2019","unstructured":"Shiori Sagawa, Pang Wei Koh, Tatsunori B Hashimoto, and Percy Liang. 2019. Distributionally Robust Neural Networks. In International Conference on Learning Representations, ICLR."},{"key":"e_1_3_2_1_43_1","unstructured":"Stephan R Sain. 1996. The nature of statistical learning theory."},{"key":"e_1_3_2_1_44_1","volume-title":"9th International Conference on Learning Representations, ICLR.","author":"Sanh Victor","unstructured":"Victor Sanh, Thomas Wolf, Yonatan Belinkov, and Alexander M. Rush. 2021. Learning from others' mistakes: Avoiding dataset biases without modeling them. In 9th International Conference on Learning Representations, ICLR."},{"key":"e_1_3_2_1_45_1","volume-title":"Daniel Filizzola, Enrico Santus, and Regina Barzilay.","author":"Schuster Tal","year":"2019","unstructured":"Tal Schuster, Darsh J. Shah, Yun Jie Serene Yeo, Daniel Filizzola, Enrico Santus, and Regina Barzilay. 2019. Towards Debiasing Fact Verification Models. In EMNLP-IJCNLP. 3417--3423."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_2_1_47_1","unstructured":"Burr Settles. 2009. Active learning literature survey. (2009)."},{"key":"e_1_3_2_1_48_1","unstructured":"Chenglei Si Zhengyan Zhang Fanchao Qi Zhiyuan Liu Yasheng Wang Qun Liu and Maosong Sun. 2021. Better robustness by more coverage: Adversarial and mixup data augmentation for robust finetuning. In Findings of the Association for Computational Linguistics: ACL-IJCNLP. 1569--1576."},{"key":"e_1_3_2_1_49_1","volume-title":"International Conference on Machine Learning, ICML. 9109--9119","author":"Srivastava Megha","year":"2020","unstructured":"Megha Srivastava, Tatsunori Hashimoto, and Percy Liang. 2020. Robustness to spurious correlations via human annotations. In International Conference on Machine Learning, ICML. 9109--9119."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21386"},{"key":"e_1_3_2_1_51_1","volume-title":"International conference on machine learning, ICML. 3319--3328","author":"Sundararajan Mukund","year":"2017","unstructured":"Mukund Sundararajan, Ankur Taly, and Qiqi Yan. 2017. Axiomatic attribution for deep networks. In International conference on machine learning, ICML. 3319--3328."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00335"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.770"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.613"},{"key":"e_1_3_2_1_55_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research, Vol. 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591693"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17651"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/579"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1101"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531850"},{"key":"e_1_3_2_1_61_1","volume-title":"9th International Conference on Learning Representations, ICLR.","author":"Xiao Kai Yuanqing","year":"2021","unstructured":"Kai Yuanqing Xiao, Logan Engstrom, Andrew Ilyas, and Aleksander Madry. 2021. Noise or Signal: The Role of Image Backgrounds in Object Recognition. In 9th International Conference on Learning Representations, ICLR."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01958"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"e_1_3_2_1_64_1","volume-title":"International Conference on Learning Representations, ICLR.","author":"Zhang Hongyi","year":"2018","unstructured":"Hongyi Zhang, Moustapha Cisse, Yann N Dauphin, and David Lopez-Paz. 2018. mixup: Beyond Empirical Risk Minimization. In International Conference on Learning Representations, ICLR."},{"key":"e_1_3_2_1_65_1","volume-title":"Proceedings of NAACL-HLT. 1298--1308","author":"Zhang Yuan","year":"2019","unstructured":"Yuan Zhang, Jason Baldridge, and Luheng He. 2019. PAWS: Paraphrase Adversaries from Word Scrambling. In Proceedings of NAACL-HLT. 1298--1308."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657729","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657729","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:42:27Z","timestamp":1755841347000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657729"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":66,"alternative-id":["10.1145\/3626772.3657729","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657729","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}