{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T19:21:07Z","timestamp":1776108067659,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":98,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T00:00:00Z","timestamp":1728604800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Schmidt Sciences","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}]},{"name":"NSF CAREER award","award":["2237693"],"award-info":[{"award-number":["2237693"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,13]]},"DOI":"10.1145\/3654777.3676362","type":"proceedings-article","created":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T10:50:36Z","timestamp":1728643836000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Clarify: Improving Model Robustness With Natural Language Corrections"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5146-5444","authenticated-orcid":false,"given":"Yoonho","family":"Lee","sequence":"first","affiliation":[{"name":"Computer Science, Stanford University, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3448-5961","authenticated-orcid":false,"given":"Michelle S.","family":"Lam","sequence":"additional","affiliation":[{"name":"Dept. of Computer Science, Stanford University, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6649-6905","authenticated-orcid":false,"given":"Helena","family":"Vasconcelos","sequence":"additional","affiliation":[{"name":"Computer Science, Stanford University, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8020-9434","authenticated-orcid":false,"given":"Michael S.","family":"Bernstein","sequence":"additional","affiliation":[{"name":"Computer Science, Stanford University, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6298-0874","authenticated-orcid":false,"given":"Chelsea","family":"Finn","sequence":"additional","affiliation":[{"name":"Computer Science, Stanford University, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Zero-Shot Robustification of Zero-Shot Models With Foundation Models. arXiv preprint arXiv:2309.04344","author":"Adila Dyah","year":"2023","unstructured":"Dyah Adila, Changho Shin, Linrong Cai, and Frederic Sala. 2023. Zero-Shot Robustification of Zero-Shot Models With Foundation Models. arXiv preprint arXiv:2309.04344 (2023)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v35i4.2513"},{"key":"e_1_3_2_1_3_1","volume-title":"International Conference on Machine Learning.","author":"Arpit Devansh","year":"2017","unstructured":"Devansh Arpit, Stanis\u0142aw Jastrzebski, Nicolas Ballas, David Krueger, Emmanuel Bengio, Maxinder\u00a0S Kanwal, Tegan Maharaj, Asja Fischer, Aaron Courville, Yoshua Bengio, 2017. A closer look at memorization in deep networks. In International Conference on Machine Learning."},{"key":"e_1_3_2_1_4_1","volume-title":"The instructional effect of feedback in test-like events. Review of educational research 61, 2","author":"Bangert-Drowns L","year":"1991","unstructured":"Robert\u00a0L Bangert-Drowns, Chen-Lin\u00a0C Kulik, James\u00a0A Kulik, and MaryTeresa Morgan. 1991. The instructional effect of feedback in test-like events. Review of educational research 61, 2 (1991), 213\u2013238."},{"key":"e_1_3_2_1_5_1","volume-title":"Learning to split for automatic bias detection. arXiv preprint arXiv:2204.13749","author":"Bao Yujia","year":"2022","unstructured":"Yujia Bao and Regina Barzilay. 2022. Learning to split for automatic bias detection. arXiv preprint arXiv:2204.13749 (2022)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/VAST.2015.7347637"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3479569"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581268"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3334480.3382839"},{"key":"e_1_3_2_1_10_1","volume-title":"Graphics Interface","author":"Chang Chia-Ming","year":"2022","unstructured":"Chia-Ming Chang, Xi Yang, and Takeo Igarashi. 2022. An Empirical Study on the Effect of Quick and Careful Labeling Styles in Image Annotation. In Graphics Interface 2022. https:\/\/openreview.net\/forum?id=SDyj8aZBPrs"},{"key":"e_1_3_2_1_11_1","volume-title":"International conference on machine learning. PMLR, 1617\u20131629","author":"Chen Mayee","year":"2021","unstructured":"Mayee Chen, Karan Goel, Nimit\u00a0S Sohoni, Fait Poms, Kayvon Fatahalian, and Christopher R\u00e9. 2021. Mandoline: Model evaluation under distribution shift. In International conference on machine learning. PMLR, 1617\u20131629."},{"key":"e_1_3_2_1_12_1","volume-title":"Altclip: Altering the language encoder in clip for extended language capabilities. arXiv preprint arXiv:2211.06679","author":"Chen Zhongzhi","year":"2022","unstructured":"Zhongzhi Chen, Guang Liu, Bo-Wen Zhang, Fulong Ye, Qinghong Yang, and Ledell Wu. 2022. Altclip: Altering the language encoder in clip for extended language capabilities. arXiv preprint arXiv:2211.06679 (2022)."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0139)","author":"Creager Elliot","year":"2021","unstructured":"Elliot Creager, Joern-Henrik Jacobsen, and Richard Zemel. 2021. Environment Inference for Invariant Learning. In Proceedings of the 38th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0139), Marina Meila and Tong Zhang (Eds.). PMLR, 2189\u20132200."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581026"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533240"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517441"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390334.1390436"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3185517"},{"key":"e_1_3_2_1_20_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Dunlap Lisa","year":"2022","unstructured":"Lisa Dunlap, Clara Mohri, Devin Guillory, Han Zhang, Trevor Darrell, Joseph\u00a0E Gonzalez, Aditi Raghunathan, and Anna Rohrbach. 2022. Using language to extend to unseen domains. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_21_1","volume-title":"Domino: Discovering systematic errors with cross-modal embeddings. arXiv preprint arXiv:2203.14960","author":"Eyuboglu Sabri","year":"2022","unstructured":"Sabri Eyuboglu, Maya Varma, Khaled Saab, Jean-Benoit Delbrouck, Christopher Lee-Messer, Jared Dunnmon, James Zou, and Christopher R\u00e9. 2022. Domino: Discovering systematic errors with cross-modal embeddings. arXiv preprint arXiv:2203.14960 (2022)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/604045.604056"},{"key":"e_1_3_2_1_23_1","volume-title":"On-the-fly Machine Learning. In International Conference on New Interfaces for Musical Expression","author":"Fiebrink Rebecca","year":"2009","unstructured":"Rebecca Fiebrink, Dan Trueman, and Perry\u00a0R. Cook. 2009. A Meta-Instrument for Interactive, On-the-fly Machine Learning. In International Conference on New Interfaces for Musical Expression (Pittsburgh, PA) (NIME \u201909)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1357054.1357061"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472749.3474734"},{"key":"e_1_3_2_1_26_1","volume-title":"Adaptive testing of computer vision models. arXiv preprint arXiv:2212.02774","author":"Gao Irena","year":"2022","unstructured":"Irena Gao, Gabriel Ilharco, Scott Lundberg, and Marco\u00a0Tulio Ribeiro. 2022. Adaptive testing of computer vision models. arXiv preprint arXiv:2212.02774 (2022)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00257-z"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the Fourth Annual Workshop on Computational Learning Theory","author":"A.","unstructured":"Sally\u00a0A. Goldman and Michael\u00a0J. Kearns. 1991. On the Complexity of Teaching. In Proceedings of the Fourth Annual Workshop on Computational Learning Theory (Santa Cruz, California, USA) (COLT \u201991). Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 303\u2013314."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1080\/07370024.2020.1734931"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","unstructured":"Maarten Grootendorst. 2020. KeyBERT: Minimal keyword extraction with BERT.https:\/\/doi.org\/10.5281\/zenodo.4461265","DOI":"10.5281\/zenodo.4461265"},{"key":"e_1_3_2_1_31_1","volume-title":"The power of feedback. Review of educational research 77, 1","author":"Hattie John","year":"2007","unstructured":"John Hattie and Helen Timperley. 2007. The power of feedback. Review of educational research 77, 1 (2007), 81\u2013112."},{"key":"e_1_3_2_1_32_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_1_33_1","volume-title":"Consequences of individual feedback on behavior in organizations.Journal of applied psychology 64, 4","author":"Ilgen R","year":"1979","unstructured":"Daniel\u00a0R Ilgen, Cynthia\u00a0D Fisher, and M\u00a0Susan Taylor. 1979. Consequences of individual feedback on behavior in organizations.Journal of applied psychology 64, 4 (1979), 349."},{"key":"e_1_3_2_1_34_1","volume-title":"Distilling model failures as directions in latent space. arXiv preprint arXiv:2206.14754","author":"Jain Saachi","year":"2022","unstructured":"Saachi Jain, Hannah Lawrence, Ankur Moitra, and Aleksander Madry. 2022. Distilling model failures as directions in latent space. arXiv preprint arXiv:2206.14754 (2022)."},{"key":"e_1_3_2_1_35_1","volume-title":"International conference on machine learning. PMLR, 4904\u20134916","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling up visual and vision-language representation learning with noisy text supervision. In International conference on machine learning. PMLR, 4904\u20134916."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491101.3503564"},{"key":"e_1_3_2_1_37_1","volume-title":"Learning the difference that makes a difference with counterfactually-augmented data. arXiv preprint arXiv:1909.12434","author":"Kaushik Divyansh","year":"2019","unstructured":"Divyansh Kaushik, Eduard Hovy, and Zachary\u00a0C Lipton. 2019. Learning the difference that makes a difference with counterfactually-augmented data. arXiv preprint arXiv:1909.12434 (2019)."},{"key":"e_1_3_2_1_38_1","volume-title":"Explaining visual biases as words by generating captions. arXiv preprint arXiv:2301.11104","author":"Kim Younghyun","year":"2023","unstructured":"Younghyun Kim, Sangwoo Mo, Minkyu Kim, Kyungmin Lee, Jaeho Lee, and Jinwoo Shin. 2023. Explaining visual biases as words by generating captions. arXiv preprint arXiv:2301.11104 (2023)."},{"key":"e_1_3_2_1_39_1","volume-title":"Last layer re-training is sufficient for robustness to spurious correlations. arXiv preprint arXiv:2204.02937","author":"Kirichenko Polina","year":"2022","unstructured":"Polina Kirichenko, Pavel Izmailov, and Andrew\u00a0Gordon Wilson. 2022. Last layer re-training is sufficient for robustness to spurious correlations. arXiv preprint arXiv:2204.02937 (2022)."},{"key":"e_1_3_2_1_40_1","volume-title":"The effects of feedback interventions on performance: a historical review, a meta-analysis, and a preliminary feedback intervention theory.Psychological bulletin 119, 2","author":"Kluger N","year":"1996","unstructured":"Avraham\u00a0N Kluger and Angelo DeNisi. 1996. The effects of feedback interventions on performance: a historical review, a meta-analysis, and a preliminary feedback intervention theory.Psychological bulletin 119, 2 (1996), 254."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3555625"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581290"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642830"},{"key":"e_1_3_2_1_44_1","unstructured":"D. Lane. 2021. Machine Learning for Kids: A Project-Based Introduction to Artificial Intelligence. No Starch Press. https:\/\/books.google.com\/books?id=g3ISEAAAQBAJ"},{"key":"e_1_3_2_1_45_1","first-page":"29348","article-title":"Mind the gap: Assessing temporal generalization in neural language models","volume":"34","author":"Lazaridou Angeliki","year":"2021","unstructured":"Angeliki Lazaridou, Adhi Kuncoro, Elena Gribovskaya, Devang Agrawal, Adam Liska, Tayfun Terzi, Mai Gimenez, Cyprien de Masson\u00a0d\u2019Autume, Tomas Kocisky, Sebastian Ruder, 2021. Mind the gap: Assessing temporal generalization in neural language models. Advances in Neural Information Processing Systems 34 (2021), 29348\u201329363.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_46_1","volume-title":"Diversify and Disambiguate: Learning From Underspecified Data. arXiv preprint arXiv:2202.03418","author":"Lee Yoonho","year":"2022","unstructured":"Yoonho Lee, Huaxiu Yao, and Chelsea Finn. 2022. Diversify and Disambiguate: Learning From Underspecified Data. arXiv preprint arXiv:2202.03418 (2022)."},{"key":"e_1_3_2_1_47_1","volume-title":"Acm Sigir Forum, Vol.\u00a029. ACM New York","author":"Lewis D","unstructured":"David\u00a0D Lewis. 1995. A sequential algorithm for training text classifiers: Corrigendum and additional data. In Acm Sigir Forum, Vol.\u00a029. ACM New York, NY, USA, 13\u201319."},{"key":"e_1_3_2_1_48_1","volume-title":"International Conference on Machine Learning. PMLR, 12888\u201312900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International Conference on Machine Learning. PMLR, 12888\u201312900."},{"key":"e_1_3_2_1_49_1","unstructured":"Zhiheng Li Ivan Evtimov Albert Gordo Caner Hazirbas Tal Hassner Cristian\u00a0Canton Ferrer Chenliang Xu and Mark Ibrahim. 2022. A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others. (2022)."},{"key":"e_1_3_2_1_50_1","volume-title":"International Conference on Machine Learning. PMLR, 6781\u20136792","author":"Liu Z","year":"2021","unstructured":"Evan\u00a0Z Liu, Behzad Haghgoo, Annie\u00a0S Chen, Aditi Raghunathan, Pang\u00a0Wei 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. PMLR, 6781\u20136792."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"e_1_3_2_1_52_1","volume-title":"Lobe: Deep Learning Made Simple. https:\/\/lobe.ai\/ Accessed: 2024-06-08.","author":"Matas M.","year":"2020","unstructured":"M. Matas, A. Menges, and M. Beissinger. 2020. Lobe: Deep Learning Made Simple. https:\/\/lobe.ai\/ Accessed: 2024-06-08."},{"key":"e_1_3_2_1_53_1","unstructured":"Microsoft. 2023. Microsoft Azure Machine Learning Studio (classic). https:\/\/studio.azureml.net\/ Accessed: 2024-06-08."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.3115\/1690219.1690287"},{"key":"e_1_3_2_1_55_1","volume-title":"Fast model editing at scale. arXiv preprint arXiv:2110.11309","author":"Mitchell Eric","year":"2021","unstructured":"Eric Mitchell, Charles Lin, Antoine Bosselut, Chelsea Finn, and Christopher\u00a0D Manning. 2021. Fast model editing at scale. arXiv preprint arXiv:2110.11309 (2021)."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/344949.344959"},{"key":"e_1_3_2_1_57_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 33 (2020), 20673\u201320684.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01851"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357236.3395454"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357236.3395454"},{"key":"e_1_3_2_1_61_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. ArXiv abs\/2303.08774 (2023)."},{"key":"e_1_3_2_1_62_1","volume-title":"Agree to Disagree: Diversity through Disagreement for Better Transferability. arXiv preprint arXiv:2202.04414","author":"Pagliardini Matteo","year":"2022","unstructured":"Matteo Pagliardini, Martin Jaggi, Fran\u00e7ois Fleuret, and Sai\u00a0Praneeth Karimireddy. 2022. Agree to Disagree: Diversity through Disagreement for Better Transferability. arXiv preprint arXiv:2202.04414 (2022)."},{"key":"e_1_3_2_1_63_1","volume-title":"Facets: Know Your Data. https:\/\/pair-code.github.io\/facets\/ Accessed: 2024-06-08.","author":"Research Initiative PAIR","year":"2017","unstructured":"PAIR People + AI Research Initiative. 2017. Facets: Know Your Data. https:\/\/pair-code.github.io\/facets\/ Accessed: 2024-06-08."},{"key":"e_1_3_2_1_64_1","unstructured":"Judea Pearl. 2009. Causality. Cambridge university press."},{"key":"e_1_3_2_1_65_1","volume-title":"Gradient Starvation: A Learning Proclivity in Neural Networks. In Advances in Neural Information Processing Systems, A.\u00a0Beygelzimer, Y.\u00a0Dauphin, P.\u00a0Liang, and J.\u00a0Wortman Vaughan (Eds.).","author":"Pezeshki Mohammad","year":"2021","unstructured":"Mohammad Pezeshki, S\u00e9kou-Oumar Kaba, Yoshua Bengio, Aaron Courville, Doina Precup, and Guillaume Lajoie. 2021. Gradient Starvation: A Learning Proclivity in Neural Networks. In Advances in Neural Information Processing Systems, A.\u00a0Beygelzimer, Y.\u00a0Dauphin, P.\u00a0Liang, and J.\u00a0Wortman Vaughan (Eds.)."},{"key":"e_1_3_2_1_66_1","volume-title":"Knowledge in organisations","author":"Polanyi Michael","unstructured":"Michael Polanyi. 2009. The tacit dimension. In Knowledge in organisations. Routledge, 135\u2013146."},{"key":"e_1_3_2_1_67_1","volume-title":"International conference on machine learning. PMLR, 8748\u20138763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748\u20138763."},{"key":"e_1_3_2_1_68_1","volume-title":"Interactive machine teaching: a human-centered approach to building machine-learned models. Human\u2013Computer Interaction 35, 5-6","author":"Ramos Gonzalo","year":"2020","unstructured":"Gonzalo Ramos, Christopher Meek, Patrice Simard, Jina Suh, and Soroush Ghorashi. 2020. Interactive machine teaching: a human-centered approach to building machine-learned models. Human\u2013Computer Interaction 35, 5-6 (2020), 413\u2013451."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.14778\/3157794.3157797"},{"key":"e_1_3_2_1_70_1","volume-title":"Tailor: Generating and perturbing text with semantic controls. arXiv preprint arXiv:2107.07150","author":"Ross Alexis","year":"2021","unstructured":"Alexis Ross, Tongshuang Wu, Hao Peng, Matthew\u00a0E Peters, and Matt Gardner. 2021. Tailor: Generating and perturbing text with semantic controls. arXiv preprint arXiv:2107.07150 (2021)."},{"key":"e_1_3_2_1_71_1","volume-title":"Estimating causal effects of treatments in randomized and nonrandomized studies.Journal of educational Psychology 66, 5","author":"Rubin B","year":"1974","unstructured":"Donald\u00a0B Rubin. 1974. Estimating causal effects of treatments in randomized and nonrandomized studies.Journal of educational Psychology 66, 5 (1974), 688."},{"key":"e_1_3_2_1_72_1","volume-title":"Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization. arXiv preprint arXiv:1911.08731","author":"Sagawa Shiori","year":"2019","unstructured":"Shiori Sagawa, Pang\u00a0Wei Koh, Tatsunori\u00a0B Hashimoto, and Percy Liang. 2019. Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization. arXiv preprint arXiv:1911.08731 (2019)."},{"key":"e_1_3_2_1_73_1","first-page":"23359","article-title":"Editing a classifier by rewriting its prediction rules","volume":"34","author":"Santurkar Shibani","year":"2021","unstructured":"Shibani Santurkar, Dimitris Tsipras, Mahalaxmi Elango, David Bau, Antonio Torralba, and Aleksander Madry. 2021. Editing a classifier by rewriting its prediction rules. Advances in Neural Information Processing Systems 34 (2021), 23359\u201323373.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3058954"},{"key":"e_1_3_2_1_75_1","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann Christoph","year":"2022","unstructured":"Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. Advances in Neural Information Processing Systems 35 (2022), 25278\u201325294.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_76_1","unstructured":"Burr Settles. 2009. Active learning literature survey. (2009)."},{"key":"e_1_3_2_1_77_1","volume-title":"Conference on Neural Information Processing Systems","author":"Shah Harshay","year":"2020","unstructured":"Harshay Shah, Kaustav Tamuly, Aditi Raghunathan, Prateek Jain, and Praneeth Netrapalli. 2020. The pitfalls of simplicity bias in neural networks. Conference on Neural Information Processing Systems (2020)."},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/3479577"},{"key":"e_1_3_2_1_79_1","unstructured":"Patrice Simard Saleema Amershi Max Chickering Alicia Edelman\u00a0Pelton Soroush Ghorashi Chris Meek Gonzalo Ramos Jina Suh Johan Verwey Mo Wang and John Wernsing. 2017. Machine Teaching: A New Paradigm for Building Machine Learning Systems. Technical Report MSR-TR-2017-26. https:\/\/www.microsoft.com\/en-us\/research\/publication\/machine-teaching-new-paradigm-building-machine-learning-systems\/"},{"key":"e_1_3_2_1_80_1","volume-title":"Machine teaching: A new paradigm for building machine learning systems. arXiv preprint arXiv:1707.06742","author":"Simard Y","year":"2017","unstructured":"Patrice\u00a0Y Simard, Saleema Amershi, David\u00a0M Chickering, Alicia\u00a0Edelman Pelton, Soroush Ghorashi, Christopher Meek, Gonzalo Ramos, Jina Suh, Johan Verwey, Mo Wang, 2017. Machine teaching: A new paradigm for building machine learning systems. arXiv preprint arXiv:1707.06742 (2017)."},{"key":"e_1_3_2_1_81_1","volume-title":"Agile Modeling: Image Classification with Domain Experts in the Loop. arXiv preprint arXiv:2302.12948","author":"Stretcu Otilia","year":"2023","unstructured":"Otilia Stretcu, Edward Vendrow, Kenji Hata, Krishnamurthy Viswanathan, Vittorio Ferrari, Sasan Tavakkol, Wenlei Zhou, Aditya Avinash, Enming Luo, Neil\u00a0Gordon Alldrin, 2023. Agile Modeling: Image Classification with Domain Experts in the Loop. arXiv preprint arXiv:2302.12948 (2023)."},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/3241379"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-demos.29"},{"key":"e_1_3_2_1_84_1","volume-title":"Mitigating Spurious Correlations by Forcing to Explore. arXiv preprint arXiv:2210.00055","author":"Taghanaki Saeid\u00a0Asgari","year":"2022","unstructured":"Saeid\u00a0Asgari Taghanaki, Aliasghar Khani, Fereshte Khani, Ali Gholami, Linh Tran, Ali Mahdavi-Amiri, and Ghassan Hamarneh. 2022. MaskTune : Mitigating Spurious Correlations by Forcing to Explore. arXiv preprint arXiv:2210.00055 (2022)."},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01626"},{"key":"e_1_3_2_1_86_1","volume-title":"The language interpretability tool: Extensible, interactive visualizations and analysis for NLP models. arXiv preprint arXiv:2008.05122","author":"Tenney Ian","year":"2020","unstructured":"Ian Tenney, James Wexler, Jasmijn Bastings, Tolga Bolukbasi, Andy Coenen, Sebastian Gehrmann, Ellen Jiang, Mahima Pushkarna, Carey Radebaugh, Emily Reif, 2020. The language interpretability tool: Extensible, interactive visualizations and analysis for NLP models. arXiv preprint arXiv:2008.05122 (2020)."},{"key":"e_1_3_2_1_87_1","volume-title":"Counterfactual invariance to spurious correlations: Why and how to pass stress tests. arXiv preprint arXiv:2106.00545","author":"Veitch Victor","year":"2021","unstructured":"Victor Veitch, Alexander D\u2019Amour, Steve Yadlowsky, and Jacob Eisenstein. 2021. Counterfactual invariance to spurious correlations: Why and how to pass stress tests. arXiv preprint arXiv:2106.00545 (2021)."},{"key":"e_1_3_2_1_88_1","volume-title":"Dataset interfaces: Diagnosing model failures using controllable counterfactual generation. arXiv preprint arXiv:2302.07865","author":"Vendrow Joshua","year":"2023","unstructured":"Joshua Vendrow, Saachi Jain, Logan Engstrom, and Aleksander Madry. 2023. Dataset interfaces: Diagnosing model failures using controllable counterfactual generation. arXiv preprint arXiv:2302.07865 (2023)."},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2934619"},{"key":"e_1_3_2_1_90_1","volume-title":"Discovering bugs in vision models using off-the-shelf image generation and captioning. arXiv preprint arXiv:2208.08831","author":"Wiles Olivia","year":"2022","unstructured":"Olivia Wiles, Isabela Albuquerque, and Sven Gowal. 2022. Discovering bugs in vision models using off-the-shelf image generation and captioning. arXiv preprint arXiv:2208.08831 (2022)."},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491101.3519729"},{"key":"e_1_3_2_1_92_1","volume-title":"Polyjuice: Generating counterfactuals for explaining, evaluating, and improving models. arXiv preprint arXiv:2101.00288","author":"Wu Tongshuang","year":"2021","unstructured":"Tongshuang Wu, Marco\u00a0Tulio Ribeiro, Jeffrey Heer, and Daniel\u00a0S Weld. 2021. Polyjuice: Generating counterfactuals for explaining, evaluating, and improving models. arXiv preprint arXiv:2101.00288 (2021)."},{"key":"e_1_3_2_1_93_1","volume-title":"Biases: Guiding Model Testing with Knowledge Bases using LLMs. arXiv preprint arXiv:2310.09668","author":"Yang Chenyang","year":"2023","unstructured":"Chenyang Yang, Rishabh Rustogi, Rachel Brower-Sinning, Grace\u00a0A Lewis, Christian K\u00e4stner, and Tongshuang Wu. 2023. Beyond Testers\u2019 Biases: Guiding Model Testing with Knowledge Bases using LLMs. arXiv preprint arXiv:2310.09668 (2023)."},{"key":"e_1_3_2_1_94_1","first-page":"8954","article-title":"Refining language models with compositional explanations","volume":"34","author":"Yao Huihan","year":"2021","unstructured":"Huihan Yao, Ying Chen, Qinyuan Ye, Xisen Jin, and Xiang Ren. 2021. Refining language models with compositional explanations. Advances in Neural Information Processing Systems 34 (2021), 8954\u20138967.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_95_1","first-page":"21682","article-title":"Contrastive adapters for foundation model group robustness","volume":"35","author":"Zhang Michael","year":"2022","unstructured":"Michael Zhang and Christopher R\u00e9. 2022. Contrastive adapters for foundation model group robustness. Advances in Neural Information Processing Systems 35 (2022), 21682\u201321697.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_96_1","volume-title":"Diagnosing and rectifying vision models using language. arXiv preprint arXiv:2302.04269","author":"Zhang Yuhui","year":"2023","unstructured":"Yuhui Zhang, Jeff\u00a0Z HaoChen, Shih-Cheng Huang, Kuan-Chieh Wang, James Zou, and Serena Yeung. 2023. Diagnosing and rectifying vision models using language. arXiv preprint arXiv:2302.04269 (2023)."},{"key":"e_1_3_2_1_97_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9761"},{"key":"e_1_3_2_1_98_1","volume-title":"An overview of machine teaching. arXiv preprint arXiv:1801.05927","author":"Zhu Xiaojin","year":"2018","unstructured":"Xiaojin Zhu, Adish Singla, Sandra Zilles, and Anna\u00a0N Rafferty. 2018. An overview of machine teaching. arXiv preprint arXiv:1801.05927 (2018)."}],"event":{"name":"UIST '24: The 37th Annual ACM Symposium on User Interface Software and Technology","location":"Pittsburgh PA USA","acronym":"UIST '24"},"container-title":["Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3654777.3676362","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3654777.3676362","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T21:12:21Z","timestamp":1754341941000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3654777.3676362"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,11]]},"references-count":98,"alternative-id":["10.1145\/3654777.3676362","10.1145\/3654777"],"URL":"https:\/\/doi.org\/10.1145\/3654777.3676362","relation":{},"subject":[],"published":{"date-parts":[[2024,10,11]]},"assertion":[{"value":"2024-10-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}