{"total":109,"rows":[{"id":"2207.04901","title":"Exploring Length Generalization in Large Language Models","created":"2022-07-11","cited_by_count":206,"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":"2306.04618","title":"Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations","created":"2023-06-07","cited_by_count":97,"area":null},{"id":"2102.00086","title":"Challenges in Automated Debiasing for Toxic Language Detection","created":"2021-01-29","cited_by_count":96,"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":"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":"2110.07736","title":"Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models","created":"2021-10-14","cited_by_count":76,"area":null},{"id":"2106.15612","title":"Learning Task Informed Abstractions","created":"2021-06-29","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":"2311.08648","title":"Explore Spurious Correlations at the Concept Level in Language Models for Text Classification","created":"2023-11-15","cited_by_count":48,"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":"2203.09125","title":"Are Vision Transformers Robust to Spurious Correlations?","created":"2022-03-17","cited_by_count":36,"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":"2210.14011","title":"Are All Spurious Features in Natural Language Alike? An Analysis through a Causal Lens","created":"2022-10-25","cited_by_count":28,"area":null},{"id":"2306.08158","title":"Sociodemographic Bias in Language Models: A Survey and Forward Path","created":"2023-06-13","cited_by_count":28,"area":null},{"id":"2105.05541","title":"Evaluating Gender Bias in Natural Language Inference","created":"2021-05-12","cited_by_count":27,"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":"2310.18555","title":"Group Robust Classification Without Any Group Information","created":"2023-10-28","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":"2305.11596","title":"Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation","created":"2023-05-19","cited_by_count":21,"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":"2210.01302","title":"Nuisances via Negativa: Adjusting for Spurious Correlations via Data Augmentation","created":"2022-10-04","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":"2205.12640","title":"Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating Spurious Correlations in Entity Typing","created":"2022-05-25","cited_by_count":16,"area":null},{"id":"2206.10816","title":"Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming","created":"2022-06-22","cited_by_count":15,"area":null},{"id":"2210.11560","title":"Finding Dataset Shortcuts with Grammar Induction","created":"2022-10-20","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":"2111.03740","title":"Toward Learning Human-aligned Cross-domain Robust Models by Countering Misaligned Features","created":"2021-11-05","cited_by_count":14,"area":null},{"id":"2210.04497","title":"Learning Robust Representations for Continual Relation Extraction via Adversarial Class Augmentation","created":"2022-10-10","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":"2201.00768","title":"Robust Natural Language Processing: Recent Advances, Challenges, and Future Directions","created":"2022-01-03","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":"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":"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":"2210.12673","title":"Lexical Generalization Improves with Larger Models and Longer Training","created":"2022-10-23","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":"2210.16978","title":"XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models","created":"2022-10-30","cited_by_count":8,"area":null},{"id":"2101.00160","title":"How Do Your Biomedical Named Entity Recognition Models Generalize to Novel Entities?","created":"2021-01-01","cited_by_count":7,"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":"2106.07240","title":"Mitigating Biases in Toxic Language Detection through Invariant Rationalization","created":"2021-06-14","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":"2210.14541","title":"Look to the Right: Mitigating Relative Position Bias in Extractive Question Answering","created":"2022-10-26","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":"2306.15268","title":"Can Pretrained Language Models Derive Correct Semantics from Corrupt Subwords under Noise?","created":"2023-06-27","cited_by_count":6,"area":null},{"id":"2103.09635","title":"SILT: Efficient transformer training for inter-lingual inference","created":"2021-03-17","cited_by_count":5,"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":"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":"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":"2209.07879","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":"2212.03230","title":"Switching to Discriminative Image Captioning by Relieving a Bottleneck of Reinforcement Learning","created":"2022-12-06","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":"2401.09615","title":"Learning Shortcuts: On the Misleading Promise of NLU in Language Models","created":"2024-01-17","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":"2110.08931","title":"Quantifying the Task-Specific Information in Text-Based Classifications","created":"2021-10-17","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":"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":"2203.06404","title":"A Proposal to Study \"Is High Quality Data All We Need?\"","created":"2022-03-12","cited_by_count":2,"area":null},{"id":"2210.16298","title":"Investigating Ensemble Methods for Model Robustness Improvement of Text Classifiers","created":"2022-10-28","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":"2302.14413","title":"SMoA: Sparse Mixture of Adapters to Mitigate Multiple Dataset Biases","created":"2023-02-28","cited_by_count":2,"area":null},{"id":"2305.03971","title":"Adaptive loose optimization for robust question answering","created":"2023-05-06","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":"2311.07556","title":"Using Natural Language Explanations to Improve Robustness of In-context Learning","created":"2023-11-13","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":"2404.16663","title":"Runtime Monitoring and Enforcement of Conditional Fairness in Generative AIs","created":"2024-04-25","cited_by_count":2,"area":null},{"id":"2506.02378","title":"Exploring Explanations Improves the Robustness of In-Context Learning","created":"2025-06-03","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":"2109.04834","title":"An Evaluation Dataset and Strategy for Building Robust Multi-turn Response Selection Model","created":"2021-09-10","cited_by_count":1,"area":null},{"id":"2201.07381","title":"Unveiling Project-Specific Bias in Neural Code Models","created":"2022-01-19","cited_by_count":1,"area":null},{"id":"2205.09934","title":"Towards Explanation for Unsupervised Graph-Level Representation Learning","created":"2022-05-20","cited_by_count":1,"area":null},{"id":"2210.07566","title":"A Survey of Parameters Associated with the Quality of Benchmarks in NLP","created":"2022-10-14","cited_by_count":1,"area":null},{"id":"2401.17498","title":"Improving QA Model Performance with Cartographic Inoculation","created":"2024-01-30","cited_by_count":1,"area":null},{"id":"2405.08793","title":"A Brief Introduction to Causal Inference in Machine Learning","created":"2024-05-14","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":"2102.04632","title":"Statistically Profiling Biases in Natural Language Reasoning Datasets and Models","created":"2021-02-09","cited_by_count":0,"area":null},{"id":"2201.03521","title":"Polish Natural Language Inference and Factivity -- an Expert-based Dataset and Benchmarks","created":"2022-01-10","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":"2304.08855","title":"A Domain-Region Based Evaluation of ML Performance Robustness to Covariate Shift","created":"2023-04-18","cited_by_count":0,"area":null},{"id":"2307.00456","title":"Make Text Unlearnable: Exploiting Effective Patterns to Protect Personal Data","created":"2023-07-02","cited_by_count":0,"area":null}],"next_cursor":"100"}