{"total":78,"rows":[{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"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":"2208.11857","title":"Shortcut Learning of Large Language Models in Natural Language Understanding","created":"2022-08-25","cited_by_count":85,"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":"2111.07367","title":"\"Will You Find These Shortcuts?\" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification","created":"2021-11-14","cited_by_count":66,"area":null},{"id":"2207.10384","title":"Detecting Shortcut Learning for Fair Medical AI using Shortcut Testing","created":"2022-07-21","cited_by_count":52,"area":null},{"id":"2510.06265","title":"Large Language Models Hallucination: A Comprehensive Survey","created":"2025-10-05","cited_by_count":49,"area":null},{"id":"2307.02394","title":"Won't Get Fooled Again: Answering Questions with False Premises","created":"2023-07-05","cited_by_count":48,"area":null},{"id":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","cited_by_count":46,"area":null},{"id":"2410.22770","title":"InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models","created":"2024-10-30","cited_by_count":42,"area":"safety"},{"id":"2110.08300","title":"The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail","created":"2021-10-15","cited_by_count":38,"area":null},{"id":"2201.12093","title":"PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddings","created":"2022-01-28","cited_by_count":29,"area":null},{"id":"2511.04655","title":"Benchmark Designers Should \"Train on the Test Set\" to Expose Exploitable Non-Visual Shortcuts","created":"2025-11-06","cited_by_count":29,"area":"mllm"},{"id":"2307.09829","title":"What do neural networks learn in image classification? A frequency shortcut perspective","created":"2023-07-19","cited_by_count":28,"area":null},{"id":"2111.01026","title":"Introspective Distillation for Robust Question Answering","created":"2021-11-01","cited_by_count":25,"area":null},{"id":"2202.05599","title":"ClidSum: A Benchmark Dataset for Cross-Lingual Dialogue Summarization","created":"2022-02-11","cited_by_count":25,"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":"2305.06024","title":"A Survey on the Robustness of Computer Vision Models against Common Corruptions","created":"2023-05-10","cited_by_count":21,"area":null},{"id":"2205.12466","title":"Eye-gaze-guided Vision Transformer for Rectifying Shortcut Learning","created":"2022-05-25","cited_by_count":20,"area":null},{"id":"2301.10908","title":"Distilling Cognitive Backdoor Patterns within an Image","created":"2023-01-26","cited_by_count":20,"area":null},{"id":"2401.12585","title":"SLANG: New Concept Comprehension of Large Language Models","created":"2024-01-23","cited_by_count":20,"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":"2405.13432","title":"Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction","created":"2024-05-22","cited_by_count":18,"area":"alignment"},{"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":"2504.12691","title":"Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations","created":"2025-04-17","cited_by_count":15,"area":null},{"id":"2206.08567","title":"Rectify ViT Shortcut Learning by Visual Saliency","created":"2022-06-17","cited_by_count":14,"area":null},{"id":"2404.01101","title":"UFID: A Unified Framework for Input-level Backdoor Detection on Diffusion Models","created":"2024-04-01","cited_by_count":14,"area":"diffusion"},{"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":"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":"2305.12641","title":"A Comprehensive Survey of Sentence Representations: From the BERT Epoch to the ChatGPT Era and Beyond","created":"2023-05-22","cited_by_count":12,"area":null},{"id":"2409.14057","title":"Co-occurrence is not Factual Association in Language Models","created":"2024-09-21","cited_by_count":12,"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":"2409.17455","title":"Navigating the Shortcut Maze: A Comprehensive Analysis of Shortcut Learning in Text Classification by Language Models","created":"2024-09-26","cited_by_count":10,"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":"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":"2310.13191","title":"Towards Robust Pruning: An Adaptive Knowledge-Retention Pruning Strategy for Language Models","created":"2023-10-19","cited_by_count":7,"area":null},{"id":"2104.07249","title":"Regularization for Long Named Entity Recognition","created":"2021-04-15","cited_by_count":5,"area":null},{"id":"2212.10392","title":"Debiasing Stance Detection Models with Counterfactual Reasoning and Adversarial Bias Learning","created":"2022-12-20","cited_by_count":5,"area":null},{"id":"2505.06032","title":"Short-circuiting Shortcuts: Mechanistic Investigation of Shortcuts in Text Classification","created":"2025-05-09","cited_by_count":5,"area":null},{"id":"2505.10930","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","created":"2025-05-16","cited_by_count":5,"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":"2302.00094","title":"The Impacts of Unanswerable Questions on the Robustness of Machine Reading Comprehension Models","created":"2023-01-31","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":"2308.06622","title":"DFM-X: Augmentation by Leveraging Prior Knowledge of Shortcut Learning","created":"2023-08-12","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":"2204.08039","title":"Pathologies of Pre-trained Language Models in Few-shot Fine-tuning","created":"2022-04-17","cited_by_count":3,"area":null},{"id":"2604.03244","title":"AI Evaluation Should Require Standardized Item-Level Data Releases","created":"2026-02-27","cited_by_count":3,"area":null},{"id":"2201.03742","title":"Explaining Predictive Uncertainty by Looking Back at Model Explanations","created":"2022-01-11","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":"2308.03795","title":"Toward Zero-Shot Instruction Following","created":"2023-08-04","cited_by_count":2,"area":null},{"id":"2308.08482","title":"Benign Shortcut for Debiasing: Fair Visual Recognition via Intervention with Shortcut Features","created":"2023-08-13","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":"2312.08677","title":"Adaptive Shortcut Debiasing for Online Continual Learning","created":"2023-12-14","cited_by_count":2,"area":null},{"id":"2312.17263","title":"TACIT: A Target-Agnostic Feature Disentanglement Framework for Cross-Domain Text Classification","created":"2023-12-25","cited_by_count":2,"area":null},{"id":"2405.14863","title":"A Nurse is Blue and Elephant is Rugby: Cross Domain Alignment in Large Language Models Reveal Human-like Patterns","created":"2024-05-23","cited_by_count":2,"area":null},{"id":"2506.06808","title":"Not quite Sherlock Holmes: Language model predictions do not reliably differentiate impossible from improbable events","created":"2025-06-07","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":"2507.09185","title":"Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models","created":"2025-07-12","cited_by_count":2,"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":"2303.02846","title":"Contrastive variational information bottleneck for aspect-based sentiment analysis","created":"2023-03-06","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":"2310.07588","title":"Accurate Use of Label Dependency in Multi-Label Text Classification Through the Lens of Causality","created":"2023-10-11","cited_by_count":1,"area":null},{"id":"2312.15848","title":"Modality-Collaborative Transformer with Hybrid Feature Reconstruction for Robust Emotion Recognition","created":"2023-12-26","cited_by_count":1,"area":null},{"id":"2401.01218","title":"Self-Supervised Position Debiasing for Large Language Models","created":"2024-01-02","cited_by_count":1,"area":null},{"id":"2402.19076","title":"Pointing out the Shortcomings of Relation Extraction Models with Semantically Motivated Adversarials","created":"2024-02-29","cited_by_count":1,"area":null},{"id":"2410.10865","title":"Generating Synthetic Datasets for Few-shot Prompt Tuning","created":"2024-10-08","cited_by_count":1,"area":"synth"},{"id":"2504.10551","title":"MiMu: Mitigating Multiple Shortcut Learning Behavior of Transformers","created":"2025-04-14","cited_by_count":1,"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":"2410.22663","title":"Automated Trustworthiness Oracle Generation for Machine Learning Text Classifiers","created":"2024-10-30","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":"2508.18407","title":"Can Out-of-Distribution Evaluations Uncover Reliance on Shortcuts? A Case Study in Question Answering","created":"2025-08-25","cited_by_count":0,"area":null},{"id":"2510.22838","title":"Semantic-Preserving Cross-Style Visual Reasoning for Robust Multi-Modal Understanding in Large Vision-Language Models","created":"2025-10-26","cited_by_count":0,"area":"lr"},{"id":"2604.12277","title":"Models Know Their Shortcuts: Deployment-Time Shortcut Mitigation","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.20915","title":"Calibration vs Decision Making: Revisiting the Reliability Paradox in Unlearned Language Models","created":"2026-05-20","cited_by_count":0,"area":"safety"}],"next_cursor":null}