{"total":83,"rows":[{"id":"2106.10328","title":"Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets","created":"2021-06-18","cited_by_count":181,"area":null},{"id":"2208.11857","title":"Shortcut Learning of Large Language Models in Natural Language Understanding","created":"2022-08-25","cited_by_count":85,"area":null},{"id":"2105.05612","title":"Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization","created":"2021-05-12","cited_by_count":83,"area":null},{"id":"2206.14754","title":"Distilling Model Failures as Directions in Latent Space","created":"2022-06-29","cited_by_count":82,"area":null},{"id":"2110.01518","title":"Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics","created":"2021-10-04","cited_by_count":67,"area":null},{"id":"2203.05818","title":"ZIN: When and How to Learn Invariance Without Environment Partition?","created":"2022-03-11","cited_by_count":58,"area":null},{"id":"2203.12942","title":"Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasets","created":"2022-03-24","cited_by_count":54,"area":null},{"id":"2104.08142","title":"Supervising Model Attention with Human Explanations for Robust Natural Language Inference","created":"2021-04-16","cited_by_count":29,"area":null},{"id":"2211.02291","title":"SelecMix: Debiased Learning by Contradicting-pair Sampling","created":"2022-11-04","cited_by_count":29,"area":null},{"id":"2305.14910","title":"From Shortcuts to Triggers: Backdoor Defense with Denoised PoE","created":"2023-05-24","cited_by_count":27,"area":null},{"id":"2305.04990","title":"Explanation-based Finetuning Makes Models More Robust to Spurious Cues","created":"2023-05-08","cited_by_count":25,"area":null},{"id":"2109.02071","title":"End-to-End Self-Debiasing Framework for Robust NLU Training","created":"2021-09-05","cited_by_count":24,"area":null},{"id":"2109.04144","title":"Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning","created":"2021-09-09","cited_by_count":23,"area":null},{"id":"2212.10563","title":"BLIND: Bias Removal With No Demographics","created":"2022-12-20","cited_by_count":22,"area":null},{"id":"2206.05263","title":"Causal Balancing for Domain Generalization","created":"2022-06-10","cited_by_count":20,"area":null},{"id":"2107.11610","title":"Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition","created":"2021-07-24","cited_by_count":19,"area":null},{"id":"2109.10164","title":"RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation","created":"2021-09-21","cited_by_count":19,"area":"distill"},{"id":"2109.04095","title":"Debiasing Methods in Natural Language Understanding Make Bias More Accessible","created":"2021-09-09","cited_by_count":17,"area":null},{"id":"2105.12628","title":"Predict then Interpolate: A Simple Algorithm to Learn Stable Classifiers","created":"2021-05-26","cited_by_count":16,"area":null},{"id":"2111.04104","title":"Uncertainty Calibration for Ensemble-Based Debiasing Methods","created":"2021-11-07","cited_by_count":16,"area":null},{"id":"2204.13749","title":"Learning to Split for Automatic Bias Detection","created":"2022-04-28","cited_by_count":16,"area":null},{"id":"2210.16079","title":"Debiasing Masks: A New Framework for Shortcut Mitigation in NLU","created":"2022-10-28","cited_by_count":16,"area":null},{"id":"2408.12942","title":"Causal-Guided Active Learning for Debiasing Large Language Models","created":"2024-08-23","cited_by_count":15,"area":null},{"id":"2104.00170","title":"Are Bias Mitigation Techniques for Deep Learning Effective?","created":"2021-04-01","cited_by_count":14,"area":null},{"id":"2110.08419","title":"Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding","created":"2021-10-16","cited_by_count":12,"area":null},{"id":"2204.02426","title":"OccamNets: Mitigating Dataset Bias by Favoring Simpler Hypotheses","created":"2022-04-05","cited_by_count":11,"area":null},{"id":"2210.07547","title":"Kernel-Whitening: Overcome Dataset Bias with Isotropic Sentence Embedding","created":"2022-10-14","cited_by_count":11,"area":null},{"id":"2302.09344","title":"Beyond Distribution Shift: Spurious Features Through the Lens of Training Dynamics","created":"2023-02-18","cited_by_count":11,"area":null},{"id":"2402.02099","title":"Analyzing the Evaluation of Cross-Lingual Knowledge Transfer in Multilingual Language Models","created":"2024-02-03","cited_by_count":11,"area":null},{"id":"2212.00921","title":"AGRO: Adversarial Discovery of Error-prone groups for Robust Optimization","created":"2022-12-02","cited_by_count":10,"area":null},{"id":"2212.05421","title":"Feature-Level Debiased Natural Language Understanding","created":"2022-12-11","cited_by_count":10,"area":null},{"id":"2305.17627","title":"Robust Natural Language Understanding with Residual Attention Debiasing","created":"2023-05-28","cited_by_count":10,"area":null},{"id":"2111.13108","title":"Combating Unknown Bias with Effective Bias-Conflicting Scoring and Gradient Alignment","created":"2021-11-25","cited_by_count":8,"area":null},{"id":"2310.08795","title":"Mitigating Bias for Question Answering Models by Tracking Bias Influence","created":"2023-10-13","cited_by_count":8,"area":null},{"id":"2411.02018","title":"Shortcut Learning in In-Context Learning: A Survey","created":"2024-11-04","cited_by_count":8,"area":null},{"id":"2102.06406","title":"A Too-Good-to-be-True Prior to Reduce Shortcut Reliance","created":"2021-02-12","cited_by_count":7,"area":null},{"id":"2112.10572","title":"General Greedy De-bias Learning","created":"2021-12-20","cited_by_count":7,"area":null},{"id":"2305.13067","title":"Distilling Robustness into Natural Language Inference Models with Domain-Targeted Augmentation","created":"2023-05-22","cited_by_count":7,"area":"distill"},{"id":"2106.07847","title":"Learning Stable Classifiers by Transferring Unstable Features","created":"2021-06-15","cited_by_count":6,"area":null},{"id":"2211.04256","title":"Bridging Fairness and Environmental Sustainability in Natural Language Processing","created":"2022-11-08","cited_by_count":5,"area":null},{"id":"2305.18917","title":"Fighting Bias with Bias: Promoting Model Robustness by Amplifying Dataset Biases","created":"2023-05-30","cited_by_count":5,"area":null},{"id":"2504.07115","title":"EqualizeIR: Mitigating Linguistic Biases in Retrieval Models","created":"2025-03-22","cited_by_count":5,"area":null},{"id":"2202.08048","title":"Decorrelate Irrelevant, Purify Relevant: Overcome Textual Spurious Correlations from a Feature Perspective","created":"2022-02-16","cited_by_count":4,"area":null},{"id":"2205.10363","title":"Robust Task-Oriented Dialogue Generation with Contrastive Pre-training and Adversarial Filtering","created":"2022-05-20","cited_by_count":4,"area":null},{"id":"2209.01824","title":"A Survey on Measuring and Mitigating Reasoning Shortcuts in Machine Reading Comprehension","created":"2022-09-05","cited_by_count":4,"area":null},{"id":"2209.07879","title":"Less is Better: Recovering Intended-Feature Subspace to Robustify NLU Models","created":"2022-09-16","cited_by_count":4,"area":null},{"id":"2306.01907","title":"A Simple yet Effective Self-Debiasing Framework for Transformer Models","created":"2023-06-02","cited_by_count":4,"area":null},{"id":"2406.01976","title":"Conditional Language Learning with Context","created":"2024-06-04","cited_by_count":4,"area":null},{"id":"2505.20209","title":"Improving the OOD Performance of Closed-Source LLMs on NLI Through Strategic Data Selection","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2108.14006","title":"A Generative Approach for Mitigating Structural Biases in Natural Language Inference","created":"2021-08-31","cited_by_count":3,"area":null},{"id":"2206.08446","title":"Methods for Estimating and Improving Robustness of Language Models","created":"2022-06-16","cited_by_count":3,"area":null},{"id":"2211.03862","title":"Looking at the Overlooked: An Analysis on the Word-Overlap Bias in Natural Language Inference","created":"2022-11-07","cited_by_count":3,"area":null},{"id":"2404.13390","title":"Explanation based Bias Decoupling Regularization for Natural Language Inference","created":"2024-04-20","cited_by_count":3,"area":null},{"id":"2109.00521","title":"Don't Discard All the Biased Instances: Investigating a Core Assumption in Dataset Bias Mitigation Techniques","created":"2021-09-01","cited_by_count":2,"area":null},{"id":"2211.13331","title":"Using Focal Loss to Fight Shallow Heuristics: An Empirical Analysis of Modulated Cross-Entropy in Natural Language Inference","created":"2022-11-23","cited_by_count":2,"area":null},{"id":"2302.02852","title":"Guide the Learner: Controlling Product of Experts Debiasing Method Based on Token Attribution Similarities","created":"2023-02-06","cited_by_count":2,"area":null},{"id":"2302.05807","title":"Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play","created":"2023-02-11","cited_by_count":2,"area":null},{"id":"2302.12538","title":"UnbiasedNets: A Dataset Diversification Framework for Robustness Bias Alleviation in Neural Networks","created":"2023-02-24","cited_by_count":2,"area":null},{"id":"2309.09380","title":"Mitigating Shortcuts in Language Models with Soft Label Encoding","created":"2023-09-17","cited_by_count":2,"area":null},{"id":"2310.06588","title":"FTFT: Efficient and Robust Fine-Tuning by Transferring Training Dynamics","created":"2023-10-10","cited_by_count":2,"area":null},{"id":"2311.00292","title":"IBADR: an Iterative Bias-Aware Dataset Refinement Framework for Debiasing NLU models","created":"2023-11-01","cited_by_count":2,"area":null},{"id":"2312.03577","title":"Improving Bias Mitigation through Bias Experts in Natural Language Understanding","created":"2023-12-06","cited_by_count":2,"area":null},{"id":"2507.05527","title":"Mitigating Shortcut Learning with InterpoLated Learning","created":"2025-07-07","cited_by_count":2,"area":null},{"id":"2510.26038","title":"Do Students Debias Like Teachers? On the Distillability of Bias Mitigation Methods","created":"2025-10-30","cited_by_count":2,"area":"distill"},{"id":"2205.09934","title":"Towards Explanation for Unsupervised Graph-Level Representation Learning","created":"2022-05-20","cited_by_count":1,"area":null},{"id":"2206.03680","title":"Improving Evaluation of Debiasing in Image Classification","created":"2022-06-08","cited_by_count":1,"area":null},{"id":"2303.02846","title":"Contrastive variational information bottleneck for aspect-based sentiment analysis","created":"2023-03-06","cited_by_count":1,"area":null},{"id":"2504.10551","title":"MiMu: Mitigating Multiple Shortcut Learning Behavior of Transformers","created":"2025-04-14","cited_by_count":1,"area":null},{"id":"2211.16550","title":"Soft Alignment Objectives for Robust Adaptation of Language Generation","created":"2022-11-29","cited_by_count":0,"area":null},{"id":"2302.11414","title":"Delving into Identify-Emphasize Paradigm for Combating Unknown Bias","created":"2023-02-22","cited_by_count":0,"area":null},{"id":"2303.16564","title":"Implicit Visual Bias Mitigation by Posterior Estimate Sharpening of a Bayesian Neural Network","created":"2023-03-29","cited_by_count":0,"area":null},{"id":"2305.02865","title":"CausalAPM: Generalizable Literal Disentanglement for NLU Debiasing","created":"2023-05-04","cited_by_count":0,"area":null},{"id":"2309.12619","title":"Learning to Diversify Neural Text Generation via Degenerative Model","created":"2023-09-22","cited_by_count":0,"area":null},{"id":"2403.14140","title":"Learning Decomposable and Debiased Representations via Attribute-Centric Information Bottlenecks","created":"2024-03-21","cited_by_count":0,"area":null},{"id":"2406.12060","title":"Not Eliminate but Aggregate: Post-Hoc Control over Mixture-of-Experts to Address Shortcut Shifts in Natural Language Understanding","created":"2024-06-17","cited_by_count":0,"area":"moe"},{"id":"2409.19766","title":"Towards Robust Extractive Question Answering Models: Rethinking the Training Methodology","created":"2024-09-29","cited_by_count":0,"area":null},{"id":"2502.11031","title":"A Critical Review of Predominant Bias in Neural Networks","created":"2025-02-16","cited_by_count":0,"area":null},{"id":"2502.18353","title":"DBR: Divergence-Based Regularization for Debiasing Natural Language Understanding Models","created":"2025-02-25","cited_by_count":0,"area":null},{"id":"2503.17632","title":"FairFlow: Mitigating Dataset Biases through Undecided Learning","created":"2025-03-22","cited_by_count":0,"area":null},{"id":"2504.12898","title":"Information Gain-Guided Causal Intervention for Autonomous Debiasing Large Language Models","created":"2025-04-17","cited_by_count":0,"area":null},{"id":"2506.23930","title":"Leveraging the Potential of Prompt Engineering for Hate Speech Detection in Low-Resource Languages","created":"2025-06-30","cited_by_count":0,"area":null},{"id":"2606.18571","title":"Fair Cognitive Impairment Detection Through Unlearning","created":"2026-06-17","cited_by_count":0,"area":"safety"},{"id":"2608.09209","title":"UNMASK: Discovering and Causally Verifying Spurious Shortcuts in Text Classifiers","created":"2026-08-10","cited_by_count":0,"area":null}],"next_cursor":null}