{"total":108,"rows":[{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639,"area":null},{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523,"area":null},{"id":"2403.19647","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","created":"2024-03-28","cited_by_count":435,"area":null},{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381,"area":null},{"id":"2108.11896","title":"A Survey on Automated Fact-Checking","created":"2021-08-26","cited_by_count":378,"area":null},{"id":"2103.08541","title":"Get Your Vitamin C! Robust Fact Verification with Contrastive Evidence","created":"2021-03-15","cited_by_count":225,"area":null},{"id":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107,"area":null},{"id":"2308.10149","title":"A Survey on Fairness in Large Language Models","created":"2023-08-20","cited_by_count":95,"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":"2103.06922","title":"Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models","created":"2021-03-11","cited_by_count":78,"area":null},{"id":"2305.00650","title":"Discover and Cure: Concept-aware Mitigation of Spurious Correlation","created":"2023-05-01","cited_by_count":71,"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":"2104.04725","title":"Fool Me Twice: Entailment from Wikipedia Gamification","created":"2021-04-10","cited_by_count":50,"area":null},{"id":"2204.07447","title":"Stretching Sentence-pair NLI Models to Reason over Long Documents and Clusters","created":"2022-04-15","cited_by_count":44,"area":null},{"id":"2107.00753","title":"An Investigation of the (In)effectiveness of Counterfactually Augmented Data","created":"2021-07-01","cited_by_count":42,"area":null},{"id":"2507.16795","title":"Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning","created":"2025-07-22","cited_by_count":39,"area":null},{"id":"2410.20011","title":"A Survey of Small Language Models","created":"2024-10-25","cited_by_count":31,"area":null},{"id":"2202.08926","title":"On Guiding Visual Attention with Language Specification","created":"2022-02-17","cited_by_count":30,"area":null},{"id":"2103.10282","title":"Modeling the Second Player in Distributionally Robust Optimization","created":"2021-03-18","cited_by_count":29,"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":"2305.14910","title":"From Shortcuts to Triggers: Backdoor Defense with Denoised PoE","created":"2023-05-24","cited_by_count":27,"area":null},{"id":"2110.08370","title":"Training Dynamics for Text Summarization Models","created":"2021-10-15","cited_by_count":25,"area":null},{"id":"2201.00072","title":"BARACK: Partially Supervised Group Robustness With Guarantees","created":"2021-12-31","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":"2210.14552","title":"A Robust Bias Mitigation Procedure Based on the Stereotype Content Model","created":"2022-10-26","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":"2312.02798","title":"Weakly Supervised Detection of Hallucinations in LLM Activations","created":"2023-12-05","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":"2202.07280","title":"Saving Dense Retriever from Shortcut Dependency in Conversational Search","created":"2022-02-15","cited_by_count":19,"area":null},{"id":"2107.04212","title":"Measuring and Improving Model-Moderator Collaboration using Uncertainty Estimation","created":"2021-07-09","cited_by_count":18,"area":null},{"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":"2104.00170","title":"Are Bias Mitigation Techniques for Deep Learning Effective?","created":"2021-04-01","cited_by_count":14,"area":null},{"id":"2205.12593","title":"Less Learn Shortcut: Analyzing and Mitigating Learning of Spurious Feature-Label Correlation","created":"2022-05-25","cited_by_count":13,"area":null},{"id":"2403.09963","title":"Take Care of Your Prompt Bias! Investigating and Mitigating Prompt Bias in Factual Knowledge Extraction","created":"2024-03-15","cited_by_count":13,"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":"2212.08570","title":"Audio-based AI classifiers show no evidence of improved COVID-19 screening over simple symptoms checkers","created":"2022-12-15","cited_by_count":12,"area":null},{"id":"2403.03375","title":"Complexity Matters: Dynamics of Feature Learning in the Presence of Spurious Correlations","created":"2024-03-05","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":"2305.13654","title":"Understanding and Mitigating Spurious Correlations in Text Classification with Neighborhood Analysis","created":"2023-05-23","cited_by_count":11,"area":null},{"id":"2312.01509","title":"Tackling Bias in Pre-trained Language Models: Current Trends and Under-represented Societies","created":"2023-12-03","cited_by_count":11,"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":"2210.12673","title":"Lexical Generalization Improves with Larger Models and Longer Training","created":"2022-10-23","cited_by_count":9,"area":null},{"id":"2211.16220","title":"Which Shortcut Solution Do Question Answering Models Prefer to Learn?","created":"2022-11-29","cited_by_count":9,"area":null},{"id":"2409.14572","title":"Evaluating the Performance and Robustness of LLMs in Materials Science Q&A and Property Predictions","created":"2024-09-22","cited_by_count":9,"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":"2112.10572","title":"General Greedy De-bias Learning","created":"2021-12-20","cited_by_count":7,"area":null},{"id":"2203.03989","title":"Adaptor: Objective-Centric Adaptation Framework for Language Models","created":"2022-03-08","cited_by_count":7,"area":null},{"id":"2210.05211","title":"A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models","created":"2022-10-11","cited_by_count":7,"area":null},{"id":"2310.06161","title":"Mitigating Simplicity Bias in Deep Learning for Improved OOD Generalization and Robustness","created":"2023-10-09","cited_by_count":7,"area":null},{"id":"2106.07847","title":"Learning Stable Classifiers by Transferring Unstable Features","created":"2021-06-15","cited_by_count":6,"area":null},{"id":"2309.06717","title":"Bias Amplification Enhances Minority Group Performance","created":"2023-09-13","cited_by_count":6,"area":null},{"id":"2104.07249","title":"Regularization for Long Named Entity Recognition","created":"2021-04-15","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":"2110.05301","title":"On a Benefit of Mask Language Modeling: Robustness to Simplicity Bias","created":"2021-10-11","cited_by_count":4,"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":"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":"2211.16202","title":"AutoCAD: Automatically Generating Counterfactuals for Mitigating Shortcut Learning","created":"2022-11-29","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":"2311.03663","title":"Principles from Clinical Research for NLP Model Generalization","created":"2023-11-07","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":"2507.11690","title":"The Impact of Coreset Selection on Spurious Correlations and Group Robustness","created":"2025-07-15","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":"2201.07614","title":"Uncovering More Shallow Heuristics: Probing the Natural Language Inference Capacities of Transformer-Based Pre-Trained Language Models Using Syllogistic Patterns","created":"2022-01-19","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":"2406.16529","title":"Towards Better Graph-based Cross-document Relation Extraction via Non-bridge Entity Enhancement and Prediction Debiasing","created":"2024-06-24","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":"2305.12123","title":"Modeling the Q-Diversity in a Min-max Play Game for Robust Optimization","created":"2023-05-20","cited_by_count":2,"area":null},{"id":"2309.04162","title":"GLS-CSC: A Simple but Effective Strategy to Mitigate Chinese STM Models' Over-Reliance on Superficial Clue","created":"2023-09-08","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":"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":"2407.19164","title":"Addressing Topic Leakage in Cross-Topic Evaluation for Authorship Verification","created":"2024-07-27","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":"2206.03680","title":"Improving Evaluation of Debiasing in Image Classification","created":"2022-06-08","cited_by_count":1,"area":null},{"id":"2210.12195","title":"Just Mix Once: Worst-group Generalization by Group Interpolation","created":"2022-10-21","cited_by_count":1,"area":null},{"id":"2305.13535","title":"Improving Classifier Robustness through Active Generation of Pairwise Counterfactuals","created":"2023-05-22","cited_by_count":1,"area":null},{"id":"2305.15130","title":"On Degrees of Freedom in Defining and Testing Natural Language Understanding","created":"2023-05-24","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":"2606.02750","title":"On the Persistent Effects of Lexicality in Large Language Models","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2109.01558","title":"Learning Neural Models for Natural Language Processing in the Face of Distributional Shift","created":"2021-09-03","cited_by_count":0,"area":null},{"id":"2210.01979","title":"GAPX: Generalized Autoregressive Paraphrase-Identification X","created":"2022-10-05","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":"2305.02865","title":"CausalAPM: Generalizable Literal Disentanglement for NLU Debiasing","created":"2023-05-04","cited_by_count":0,"area":null}],"next_cursor":"100"}