{"total":81,"rows":[{"id":"2110.08420","title":"Understanding Dataset Difficulty with $\\mathcal{V}$-Usable Information","created":"2021-10-16","cited_by_count":291,"area":null},{"id":"2201.05955","title":"WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation","created":"2022-01-16","cited_by_count":202,"area":null},{"id":"2210.13966","title":"The Debate Over Understanding in AI's Large Language Models","created":"2022-10-14","cited_by_count":142,"area":null},{"id":"2303.01432","title":"WiCE: Real-World Entailment for Claims in Wikipedia","created":"2023-03-02","cited_by_count":120,"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":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91,"area":null},{"id":"2109.01653","title":"CREAK: A Dataset for Commonsense Reasoning over Entity Knowledge","created":"2021-09-03","cited_by_count":88,"area":null},{"id":"2107.07150","title":"Tailor: Generating and Perturbing Text with Semantic Controls","created":"2021-07-15","cited_by_count":68,"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":"2203.12942","title":"Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasets","created":"2022-03-24","cited_by_count":54,"area":null},{"id":"2105.13947","title":"Changing the World by Changing the Data","created":"2021-05-28","cited_by_count":51,"area":null},{"id":"2310.10383","title":"Privacy in Large Language Models: Attacks, Defenses and Future Directions","created":"2023-10-16","cited_by_count":51,"area":null},{"id":"2107.00323","title":"Combining Feature and Instance Attribution to Detect Artifacts","created":"2021-07-01","cited_by_count":38,"area":null},{"id":"2202.12350","title":"DoCoGen: Domain Counterfactual Generation for Low Resource Domain Adaptation","created":"2022-02-24","cited_by_count":37,"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":"2305.14910","title":"From Shortcuts to Triggers: Backdoor Defense with Denoised PoE","created":"2023-05-24","cited_by_count":27,"area":null},{"id":"2210.04873","title":"CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation","created":"2022-10-10","cited_by_count":24,"area":null},{"id":"2212.10563","title":"BLIND: Bias Removal With No Demographics","created":"2022-12-20","cited_by_count":22,"area":null},{"id":"2204.04487","title":"Informativeness and Invariance: Two Perspectives on Spurious Correlations in Natural Language","created":"2022-04-09","cited_by_count":21,"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":"2603.13285","title":"Brittlebench: Quantifying LLM robustness via prompt sensitivity","created":"2026-02-27","cited_by_count":21,"area":null},{"id":"2308.07120","title":"Position: Key Claims in LLM Research Have a Long Tail of Footnotes","created":"2023-08-14","cited_by_count":20,"area":null},{"id":"2204.12708","title":"On the Limitations of Dataset Balancing: The Lost Battle Against Spurious Correlations","created":"2022-04-27","cited_by_count":19,"area":null},{"id":"2203.06498","title":"The worst of both worlds: A comparative analysis of errors in learning from data in psychology and machine learning","created":"2022-03-12","cited_by_count":17,"area":null},{"id":"2403.17368","title":"ChatGPT Rates Natural Language Explanation Quality Like Humans: But on Which Scales?","created":"2024-03-26","cited_by_count":17,"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":"2210.11560","title":"Finding Dataset Shortcuts with Grammar Induction","created":"2022-10-20","cited_by_count":15,"area":null},{"id":"2212.09676","title":"Words as Gatekeepers: Measuring Discipline-specific Terms and Meanings in Scholarly Publications","created":"2022-12-19","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":"2209.07430","title":"Machine Reading, Fast and Slow: When Do Models \"Understand\" Language?","created":"2022-09-15","cited_by_count":13,"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":"2305.17627","title":"Robust Natural Language Understanding with Residual Attention Debiasing","created":"2023-05-28","cited_by_count":10,"area":null},{"id":"2405.00588","title":"Are Models Biased on Text without Gender-related Language?","created":"2024-05-01","cited_by_count":10,"area":null},{"id":"2112.08321","title":"Know Thy Strengths: Comprehensive Dialogue State Tracking Diagnostics","created":"2021-12-15","cited_by_count":9,"area":null},{"id":"2210.06799","title":"Benchmarking Long-tail Generalization with Likelihood Splits","created":"2022-10-13","cited_by_count":9,"area":null},{"id":"2210.13575","title":"Does Self-Rationalization Improve Robustness to Spurious Correlations?","created":"2022-10-24","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":"2309.04992","title":"Mitigating Word Bias in Zero-shot Prompt-based Classifiers","created":"2023-09-10","cited_by_count":9,"area":null},{"id":"2410.11672","title":"Leaving the barn door open for Clever Hans: Simple features predict LLM benchmark answers","created":"2024-10-15","cited_by_count":9,"area":null},{"id":"2112.09237","title":"PECO: Examining Single Sentence Label Leakage in Natural Language Inference Datasets through Progressive Evaluation of Cluster Outliers","created":"2021-12-16","cited_by_count":8,"area":null},{"id":"2305.07984","title":"SCENE: Self-Labeled Counterfactuals for Extrapolating to Negative Examples","created":"2023-05-13","cited_by_count":8,"area":null},{"id":"2310.16607","title":"On the Interplay between Fairness and Explainability","created":"2023-10-25","cited_by_count":7,"area":null},{"id":"2210.06725","title":"Assessing Out-of-Domain Language Model Performance from Few Examples","created":"2022-10-13","cited_by_count":6,"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":"2306.04610","title":"The Two Word Test: A Semantic Benchmark for Large Language Models","created":"2023-06-07","cited_by_count":5,"area":null},{"id":"2210.13439","title":"Cascading Biases: Investigating the Effect of Heuristic Annotation Strategies on Data and Models","created":"2022-10-24","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":"2306.10727","title":"Jamp: Controlled Japanese Temporal Inference Dataset for Evaluating Generalization Capacity of Language Models","created":"2023-06-19","cited_by_count":4,"area":null},{"id":"2306.12146","title":"Which Spurious Correlations Impact Reasoning in NLI Models? A Visual Interactive Diagnosis through Data-Constrained Counterfactuals","created":"2023-06-21","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":"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":"2305.13658","title":"Understanding Compositional Data Augmentation in Typologically Diverse Morphological Inflection","created":"2023-05-23","cited_by_count":3,"area":null},{"id":"2305.15389","title":"Comparing Humans and Models on a Similar Scale: Towards Cognitive Gender Bias Evaluation in Coreference Resolution","created":"2023-05-24","cited_by_count":3,"area":null},{"id":"2306.02190","title":"Stubborn Lexical Bias in Data and Models","created":"2023-06-03","cited_by_count":3,"area":null},{"id":"2205.12228","title":"When More Data Hurts: A Troubling Quirk in Developing Broad-Coverage Natural Language Understanding Systems","created":"2022-05-24","cited_by_count":2,"area":null},{"id":"2211.05485","title":"Understanding Text Classification Data and Models Using Aggregated Input Salience","created":"2022-11-10","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":"2302.14413","title":"SMoA: Sparse Mixture of Adapters to Mitigate Multiple Dataset Biases","created":"2023-02-28","cited_by_count":2,"area":null},{"id":"2505.20959","title":"Research Community Perspectives on \"Intelligence\" and Large Language Models","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2506.05970","title":"Let's Put Ourselves in Sally's Shoes: Shoes-of-Others Prefilling Improves Theory of Mind in Large Language Models","created":"2025-06-06","cited_by_count":2,"area":null},{"id":"2112.06733","title":"Measuring Context-Word Biases in Lexical Semantic Datasets","created":"2021-12-13","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":"2212.08756","title":"Multi-Scales Data Augmentation Approach In Natural Language Inference For Artifacts Mitigation And Pre-Trained Model Optimization","created":"2022-12-16","cited_by_count":1,"area":null},{"id":"2305.14104","title":"Out-of-Distribution Generalization in Text Classification: Past, Present, and Future","created":"2023-05-23","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":"2310.16261","title":"The Distributional Hypothesis Does Not Fully Explain the Benefits of Masked Language Model Pretraining","created":"2023-10-25","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":"2210.01734","title":"Text Characterization Toolkit","created":"2022-10-04","cited_by_count":0,"area":null},{"id":"2311.09605","title":"Measuring and Improving Attentiveness to Partial Inputs with Counterfactuals","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2312.08747","title":"Dissecting vocabulary biases datasets through statistical testing and automated data augmentation for artifact mitigation in Natural Language Inference","created":"2023-12-14","cited_by_count":0,"area":null},{"id":"2401.13907","title":"No More Distractions: an Adaptive Up-Sampling Algorithm to Reduce Data Artifacts","created":"2024-01-25","cited_by_count":0,"area":null},{"id":"2408.05497","title":"MABR: Multilayer Adversarial Bias Removal Without Prior Bias Knowledge","created":"2024-08-10","cited_by_count":0,"area":null},{"id":"2410.09642","title":"RepMatch: Quantifying Cross-Instance Similarities in Representation Space","created":"2024-10-12","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":"2504.05902","title":"Defending against Backdoor Attacks via Module Switching","created":"2025-04-08","cited_by_count":0,"area":null},{"id":"2507.21302","title":"Can human clinical rationales improve the performance and explainability of clinical text classification models?","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2604.16787","title":"When Informal Text Breaks NLI: Tokenization Failure, Distribution Shift, and Targeted Mitigations","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2605.18801","title":"Position: Let's Develop Data Probes to Fundamentally Understand How Data Affects LLM Performance","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2608.09209","title":"UNMASK: Discovering and Causally Verifying Spurious Shortcuts in Text Classifiers","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.13003","title":"Judging by the Cover: Cleaning LLM Truthfulness Benchmarks to Avoid Surface-Level Feature Leakage","created":"2026-09-11","cited_by_count":0,"area":null}],"next_cursor":null}