Learning to Model and Ignore Dataset Bias with Mixed Capacity Ensembles

7 November 2020

Luke Zettlemoyer

Papers citing "Learning to Model and Ignore Dataset Bias with Mixed Capacity Ensembles"

42 / 42 papers shown

Title
How to Improve the Robustness of Closed-Source Models on NLI Joe Stacey Lisa Alazraki Aran Ubhi Beyza Ermis Aaron Mueller Marek Rei 156 0 0 26 May 2025
Towards Robust Extractive Question Answering Models: Rethinking the Training MethodologyConference on Empirical Methods in Natural Language Processing (EMNLP), 2024 Son Quoc Tran Matt Kretchmar OOD 98 0 0 29 Sep 2024
Not Eliminate but Aggregate: Post-Hoc Control over Mixture-of-Experts to Address Shortcut Shifts in Natural Language Understanding Ukyo Honda Tatsushi Oka Peinan Zhang Masato Mita 156 1 0 17 Jun 2024
Conditional Language Learning with Context X. Zhang Chenyi Guo Ji Wu 138 5 0 04 Jun 2024
Improving Bias Mitigation through Bias Experts in Natural Language Understanding Eojin Jeon Mingyu Lee Juhyeong Park Yeachan Kim Wing-Lam Mok SangKeun Lee 83 2 0 06 Dec 2023
Explore Spurious Correlations at the Concept Level in Language Models for Text ClassificationAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 Yuhang Zhou Paiheng Xu Xiaoyu Liu Bang An Wei Ai Furong Huang LRM 271 40 0 15 Nov 2023
Robust Visual Question Answering: Datasets, Methods, and Future ChallengesIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023 Jie Ma Pinghui Wang Dechen Kong Zewei Wang Jun Liu Hongbin Pei Junzhou Zhao OOD 172 38 0 21 Jul 2023
Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs EvaluationsNeural Information Processing Systems (NeurIPS), 2023 Lifan Yuan Yangyi Chen Ganqu Cui Hongcheng Gao Fangyuan Zou Xingyi Cheng Heng Ji Zhiyuan Liu Maosong Sun 214 107 0 07 Jun 2023
A Simple yet Effective Self-Debiasing Framework for Transformer ModelsArtificial Intelligence (AIJ), 2023 Xiaoyue Wang Lijie Wang Xin Liu Suhang Wu Jinsong Su Huasen Wu 103 4 0 02 Jun 2023
From Shortcuts to Triggers: Backdoor Defense with Denoised PoENorth American Chapter of the Association for Computational Linguistics (NAACL), 2023 Qin Liu Fei Wang Chaowei Xiao Muhao Chen AAML 177 26 0 24 May 2023
Understanding and Mitigating Spurious Correlations in Text Classification with Neighborhood AnalysisFindings (Findings), 2023 Oscar Chew Hsuan-Tien Lin Kai-Wei Chang Kuan-Hao Huang 178 7 0 23 May 2023
Improving Classifier Robustness through Active Generation of Pairwise Counterfactuals Ananth Balashankar Xuezhi Wang Yao Qin Ben Packer Nithum Thain Jilin Chen Ed H. Chi Alex Beutel 94 1 0 22 May 2023
CausalAPM: Generalizable Literal Disentanglement for NLU Debiasing Songyang Gao Jiajun Sun Junjie Shan Tao Gui Xuanjing Huang CML 93 0 0 04 May 2023
Contrastive variational information bottleneck for aspect-based sentiment analysisKnowledge-Based Systems (KBS), 2023 Ming-Wei Chang Min Yang Qingshan Jiang Ruifeng Xu 154 6 0 06 Mar 2023
Delving into Identify-Emphasize Paradigm for Combating Unknown BiasInternational Journal of Computer Vision (IJCV), 2023 Bowen Zhao Chen Chen Qian-Wei Wang Anfeng He Shutao Xia 120 1 0 22 Feb 2023
Using Focal Loss to Fight Shallow Heuristics: An Empirical Analysis of Modulated Cross-Entropy in Natural Language Inference Frano Rajic Ivan Stresec Axel Marmet Tim Postuvan 86 3 0 23 Nov 2022
Less is Better: Recovering Intended-Feature Subspace to Robustify NLU ModelsInternational Conference on Computational Linguistics (COLING), 2022 Ting Wu Tao Gui 105 5 0 16 Sep 2022
Distribution Aware Metrics for Conditional Natural Language GenerationInternational Conference on Language Resources and Evaluation (LREC), 2022 David M. Chan Yiming Ni David A. Ross Sudheendra Vijayanarasimhan Austin Myers John F. Canny 216 4 0 15 Sep 2022
What's in a Caption? Dataset-Specific Linguistic Diversity and Its Effect on Visual Description Models and Metrics David M. Chan Austin Myers Sudheendra Vijayanarasimhan David A. Ross Bryan Seybold John F. Canny 101 6 0 12 May 2022
OccamNets: Mitigating Dataset Bias by Favoring Simpler HypothesesEuropean Conference on Computer Vision (ECCV), 2022 Robik Shrestha Kushal Kafle Christopher Kanan CML 220 14 0 05 Apr 2022
On Guiding Visual Attention with Language SpecificationComputer Vision and Pattern Recognition (CVPR), 2022 Suzanne Petryk Lisa Dunlap Keyan Nasseri Joseph E. Gonzalez Trevor Darrell Anna Rohrbach VLM 313 37 1 17 Feb 2022
Decorrelate Irrelevant, Purify Relevant: Overcome Textual Spurious Correlations from a Feature PerspectiveInternational Conference on Computational Linguistics (COLING), 2022 Jiajun Sun Rui Zheng Ting Wu Songyang Gao Junjie Shan Tao Gui Yueming Wu Xuanjing Huang 180 11 0 16 Feb 2022
General Greedy De-bias LearningIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021 Xinzhe Han Shuhui Wang Chi Su Qingming Huang Qi Tian 243 13 0 20 Dec 2021
Measure and Improve Robustness in NLP Models: A Survey Xuezhi Wang Haohan Wang Diyi Yang 364 150 0 15 Dec 2021
Combating Unknown Bias with Effective Bias-Conflicting Scoring and Gradient Alignment Bowen Zhao Chen Chen Qian-Wei Wang Anfeng He Shutao Xia 98 10 0 25 Nov 2021
Uncertainty Calibration for Ensemble-Based Debiasing Methods Ruibin Xiong Yimeng Chen Liang Pang Xueqi Chen Yanyan Lan 96 22 0 07 Nov 2021
Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models Tianlu Wang Rohit Sridhar Diyi Yang Xuezhi Wang AAML 260 82 0 14 Oct 2021
Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics Prajjwal Bhargava Aleksandr Drozd Anna Rogers 214 116 0 04 Oct 2021
Avoiding Inference Heuristics in Few-shot Prompt-based FinetuningConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 Prasetya Ajie Utama N. Moosavi Victor Sanh Iryna Gurevych AAML 158 36 0 09 Sep 2021
End-to-End Self-Debiasing Framework for Robust NLU Training Abbas Ghaddar Philippe Langlais Mehdi Rezagholizadeh Ahmad Rashid UQCV 109 41 0 05 Sep 2021
Don't Discard All the Biased Instances: Investigating a Core Assumption in Dataset Bias Mitigation TechniquesConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 Hossein Amirkhani Mohammad Taher Pilehvar 90 6 0 01 Sep 2021
Context-aware Adversarial Training for Name Regularity Bias in Named Entity RecognitionTransactions of the Association for Computational Linguistics (TACL), 2021 Abbas Ghaddar Philippe Langlais Ahmad Rashid Mehdi Rezagholizadeh 174 45 0 24 Jul 2021
X-GGM: Graph Generative Modeling for Out-of-Distribution Generalization in Visual Question AnsweringACM Multimedia (ACM MM), 2021 Jingjing Jiang Zi-yi Liu Yifan Liu Jingjing Jiang N. Zheng OOD 125 20 0 24 Jul 2021
A Survey on Bias in Visual DatasetsComputer Vision and Image Understanding (CVIU), 2021 Simone Fabbrizzi Symeon Papadopoulos Eirini Ntoutsi Y. Kompatsiaris 280 142 0 16 Jul 2021
Learning Task Informed AbstractionsInternational Conference on Machine Learning (ICML), 2021 Xiang Fu Ge Yang Pulkit Agrawal Tommi Jaakkola 164 70 0 29 Jun 2021
Demoting the Lead Bias in News Summarization via Alternating Adversarial LearningAnnual Meeting of the Association for Computational Linguistics (ACL), 2021 Linzi Xing Wen Xiao Giuseppe Carenini 134 19 0 29 May 2021
Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD GeneralizationComputer Vision and Pattern Recognition (CVPR), 2021 Damien Teney Ehsan Abbasnejad Simon Lucey Anton Van Den Hengel 282 99 0 12 May 2021
Competency Problems: On Finding and Removing Artifacts in Language DataConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 Matt Gardner William Merrill Jesse Dodge Matthew E. Peters Alexis Ross Sameer Singh Noah A. Smith 360 114 0 17 Apr 2021
Supervising Model Attention with Human Explanations for Robust Natural Language InferenceAAAI Conference on Artificial Intelligence (AAAI), 2021 Joe Stacey Yonatan Belinkov Marek Rei 119 49 0 16 Apr 2021
How to Train BERT with an Academic BudgetConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 Peter Izsak Moshe Berchansky Omer Levy 241 125 0 15 Apr 2021
Improved and efficient inter-vehicle distance estimation using road gradients of both ego and target vehiclesInternational Conference on Autonomic and Autonomous Systems (ICAAS), 2021 Robik Shrestha Jinkyu Lee Kushal Kafle S. Hwang Il Yong Chun 103 1 0 01 Apr 2021
A Too-Good-to-be-True Prior to Reduce Shortcut ReliancePattern Recognition Letters (PR), 2021 Nikolay Dagaev Brett D. Roads Xiaoliang Luo Daniel N. Barry Kaustubh R. Patil Bradley C. Love 147 10 0 12 Feb 2021