{"total":99,"rows":[{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463,"area":null},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"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":"2101.00288","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","created":"2021-01-01","cited_by_count":222,"area":null},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156,"area":null},{"id":"2102.12060","title":"Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing","created":"2021-02-24","cited_by_count":126,"area":null},{"id":"2305.18029","title":"Faithfulness Tests for Natural Language Explanations","created":"2023-05-29","cited_by_count":107,"area":null},{"id":"2401.07927","title":"Are self-explanations from Large Language Models faithful?","created":"2024-01-15","cited_by_count":101,"area":null},{"id":"2103.01378","title":"Contrastive Explanations for Model Interpretability","created":"2021-03-02","cited_by_count":75,"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":"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":"2105.06965","title":"Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction","created":"2021-05-14","cited_by_count":59,"area":null},{"id":"2106.06823","title":"Prompting Contrastive Explanations for Commonsense Reasoning Tasks","created":"2021-06-12","cited_by_count":45,"area":null},{"id":"2102.12982","title":"A Primer on Contrastive Pretraining in Language Processing: Methods, Lessons Learned and Perspectives","created":"2021-02-25","cited_by_count":41,"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":"2210.06929","title":"On the Explainability of Natural Language Processing Deep Models","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2305.14791","title":"Prompting Large Language Models for Counterfactual Generation: An Empirical Study","created":"2023-05-24","cited_by_count":37,"area":null},{"id":"2110.13880","title":"Understanding Interlocking Dynamics of Cooperative Rationalization","created":"2021-10-26","cited_by_count":36,"area":null},{"id":"2311.05014","title":"Interpreting Pretrained Language Models via Concept Bottlenecks","created":"2023-11-08","cited_by_count":33,"area":null},{"id":"2305.09770","title":"ConvXAI: Delivering Heterogeneous AI Explanations via Conversations to Support Human-AI Scientific Writing","created":"2023-05-16","cited_by_count":31,"area":null},{"id":"2405.00722","title":"LLMs for Generating and Evaluating Counterfactuals: A Comprehensive Study","created":"2024-04-26","cited_by_count":31,"area":null},{"id":"2110.07596","title":"Retrieval-guided Counterfactual Generation for QA","created":"2021-10-14","cited_by_count":29,"area":null},{"id":"2208.01575","title":"ferret: a Framework for Benchmarking Explainers on Transformers","created":"2022-08-02","cited_by_count":26,"area":null},{"id":"2111.05711","title":"Counterfactual Explanations for Models of Code","created":"2021-11-10","cited_by_count":25,"area":null},{"id":"2311.01270","title":"People Make Better Edits: Measuring the Efficacy of LLM-Generated Counterfactually Augmented Data for Harmful Language Detection","created":"2023-11-02","cited_by_count":25,"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":"2305.17075","title":"CREST: A Joint Framework for Rationalization and Counterfactual Text Generation","created":"2023-05-26","cited_by_count":24,"area":null},{"id":"2407.03993","title":"A Survey on Natural Language Counterfactual Generation","created":"2024-07-04","cited_by_count":21,"area":null},{"id":"2206.03945","title":"Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models","created":"2022-06-08","cited_by_count":20,"area":null},{"id":"2205.03302","title":"Necessity and Sufficiency for Explaining Text Classifiers: A Case Study in Hate Speech Detection","created":"2022-05-06","cited_by_count":18,"area":null},{"id":"2106.05894","title":"Synthesizing Adversarial Negative Responses for Robust Response Ranking and Evaluation","created":"2021-06-10","cited_by_count":16,"area":null},{"id":"2401.12576","title":"LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-Explanations","created":"2024-01-23","cited_by_count":16,"area":null},{"id":"2205.00130","title":"ExSum: From Local Explanations to Model Understanding","created":"2022-04-30","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":"2404.17475","title":"CEval: A Benchmark for Evaluating Counterfactual Text Generation","created":"2024-04-26","cited_by_count":15,"area":null},{"id":"2206.13757","title":"Flexible text generation for counterfactual fairness probing","created":"2022-06-28","cited_by_count":13,"area":null},{"id":"2312.15033","title":"Sparsity-Guided Holistic Explanation for LLMs with Interpretable Inference-Time Intervention","created":"2023-12-22","cited_by_count":12,"area":null},{"id":"2205.12469","title":"Logical Satisfiability of Counterfactuals for Faithful Explanations in NLI","created":"2022-05-25","cited_by_count":11,"area":null},{"id":"2109.07713","title":"Transferable Persona-Grounded Dialogues via Grounded Minimal Edits","created":"2021-09-16","cited_by_count":10,"area":null},{"id":"2109.07983","title":"Let the CAT out of the bag: Contrastive Attributed explanations for Text","created":"2021-09-16","cited_by_count":9,"area":null},{"id":"2203.17081","title":"Interpretation of Black Box NLP Models: A Survey","created":"2022-03-31","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":"2505.22830","title":"What Has Been Lost with Synthetic Evaluation?","created":"2025-05-28","cited_by_count":9,"area":null},{"id":"2104.08735","title":"Learning with Instance Bundles for Reading Comprehension","created":"2021-04-18","cited_by_count":8,"area":null},{"id":"2304.11721","title":"A Lightweight Constrained Generation Alternative for Query-focused Summarization","created":"2023-04-23","cited_by_count":8,"area":null},{"id":"2304.12425","title":"TIGTEC : Token Importance Guided TExt Counterfactuals","created":"2023-04-24","cited_by_count":8,"area":null},{"id":"2305.18623","title":"Alfred: A System for Prompted Weak Supervision","created":"2023-05-29","cited_by_count":8,"area":null},{"id":"2312.01582","title":"Explaining with Contrastive Phrasal Highlighting: A Case Study in Assisting Humans to Detect Translation Differences","created":"2023-12-04","cited_by_count":8,"area":null},{"id":"2403.20322","title":"Towards a Framework for Evaluating Explanations in Automated Fact Verification","created":"2024-03-29","cited_by_count":7,"area":null},{"id":"2406.16342","title":"Is your benchmark truly adversarial? AdvScore: Evaluating Human-Grounded Adversarialness","created":"2024-06-24","cited_by_count":7,"area":null},{"id":"2601.03775","title":"Do LLM Self-Explanations Help Users Predict Model Behavior? Evaluating Counterfactual Simulatability with Pragmatic Perturbations","created":"2026-01-07","cited_by_count":7,"area":null},{"id":"2209.00445","title":"Interpreting Embedding Spaces by Conceptualization","created":"2022-08-22","cited_by_count":6,"area":null},{"id":"2305.17055","title":"Counterfactuals of Counterfactuals: a back-translation-inspired approach to analyse counterfactual editors","created":"2023-05-26","cited_by_count":6,"area":null},{"id":"2501.00777","title":"FitCF: A Framework for Automatic Feature Importance-guided Counterfactual Example Generation","created":"2025-01-01","cited_by_count":6,"area":null},{"id":"2503.18185","title":"Exploring Energy Landscapes for Minimal Counterfactual Explanations: Applications in Cybersecurity and Beyond","created":"2025-03-23","cited_by_count":6,"area":null},{"id":"2211.11160","title":"Unsupervised Explanation Generation via Correct Instantiations","created":"2022-11-21","cited_by_count":5,"area":null},{"id":"2301.02299","title":"Sequentially Controlled Text Generation","created":"2023-01-05","cited_by_count":5,"area":null},{"id":"2310.07819","title":"Faithfulness Measurable Masked Language Models","created":"2023-10-11","cited_by_count":5,"area":null},{"id":"2310.16955","title":"Break it, Imitate it, Fix it: Robustness by Generating Human-Like Attacks","created":"2023-10-25","cited_by_count":5,"area":null},{"id":"2411.02643","title":"A Comparative Analysis of Counterfactual Explanation Methods for Text Classifiers","created":"2024-11-04","cited_by_count":5,"area":null},{"id":"2505.03132","title":"VISLIX: An XAI Framework for Validating Vision Models with Slice Discovery and Analysis","created":"2025-05-06","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":"2505.13972","title":"Truth or Twist? Optimal Model Selection for Reliable Label Flipping Evaluation in LLM-based Counterfactuals","created":"2025-05-20","cited_by_count":5,"area":null},{"id":"2601.00282","title":"Can Large Language Models Still Explain Themselves? Investigating the Impact of Quantization on Self-Explanations","created":"2026-01-01","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":"2402.18678","title":"RORA: Robust Free-Text Rationale Evaluation","created":"2024-02-28","cited_by_count":4,"area":null},{"id":"2103.14973","title":"Explaining the Road Not Taken","created":"2021-03-27","cited_by_count":3,"area":null},{"id":"2307.01900","title":"Concept-Based Explanations to Test for False Causal Relationships Learned by Abusive Language Classifiers","created":"2023-07-04","cited_by_count":3,"area":null},{"id":"2408.11252","title":"Counterfactuals As a Means for Evaluating Faithfulness of Attribution Methods in Autoregressive Language Models","created":"2024-08-21","cited_by_count":3,"area":null},{"id":"2503.04463","title":"Guiding LLMs to Generate High-Fidelity and High-Quality Counterfactual Explanations for Text Classification","created":"2025-03-06","cited_by_count":3,"area":null},{"id":"2508.18933","title":"VISION: Robust and Interpretable Code Vulnerability Detection Leveraging Counterfactual Augmentation","created":"2025-08-26","cited_by_count":3,"area":null},{"id":"2206.10429","title":"Plug and Play Counterfactual Text Generation for Model Robustness","created":"2022-06-21","cited_by_count":2,"area":null},{"id":"2211.00369","title":"A General Search-based Framework for Generating Textual Counterfactual Explanations","created":"2022-11-01","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":"2211.05987","title":"CCPrefix: Counterfactual Contrastive Prefix-Tuning for Many-Class Classification","created":"2022-11-11","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":"2405.08468","title":"Challenges and Opportunities in Text Generation Explainability","created":"2024-05-14","cited_by_count":2,"area":null},{"id":"2405.09948","title":"Mitigating Text Toxicity with Counterfactual Generation","created":"2024-05-16","cited_by_count":2,"area":null},{"id":"2204.13192","title":"Counterfactual Explanations for Natural Language Interfaces","created":"2022-04-27","cited_by_count":1,"area":null},{"id":"2205.01588","title":"SparCAssist: A Model Risk Assessment Assistant Based on Sparse Generated Counterfactuals","created":"2022-05-03","cited_by_count":1,"area":null},{"id":"2205.10932","title":"Argumentative Explanations for Pattern-Based Text Classifiers","created":"2022-05-22","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":"2404.14943","title":"Does It Make Sense to Explain a Black Box With Another Black Box?","created":"2024-04-23","cited_by_count":1,"area":null},{"id":"2408.01969","title":"Optimal and efficient text counterfactuals using Graph Neural Networks","created":"2024-08-04","cited_by_count":1,"area":null},{"id":"2410.11444","title":"A Theoretical Survey on Foundation Models","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2503.16444","title":"Conversational Explanations: Discussing Explainable AI with Non-AI Experts","created":"2025-02-16","cited_by_count":1,"area":null},{"id":"2601.00263","title":"Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generation","created":"2026-01-01","cited_by_count":1,"area":null},{"id":"2601.01446","title":"iFlip: Iterative Feedback-driven Counterfactual Example Refinement","created":"2026-01-04","cited_by_count":1,"area":null},{"id":"2210.08902","title":"Beyond Model Interpretability: On the Faithfulness and Adversarial Robustness of Contrastive Textual Explanations","created":"2022-10-17","cited_by_count":0,"area":null},{"id":"2312.08724","title":"Personalized Path Recourse for Reinforcement Learning Agents","created":"2023-12-14","cited_by_count":0,"area":null},{"id":"2403.15492","title":"Visual Analytics for Fine-grained Text Classification Models and Datasets","created":"2024-03-21","cited_by_count":0,"area":null},{"id":"2406.11785","title":"CELL your Model: Contrastive Explanations for Large Language Models","created":"2024-06-17","cited_by_count":0,"area":null},{"id":"2410.12511","title":"Advancing Fairness in Natural Language Processing: From Traditional Methods to Explainability","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2411.00056","title":"Generating Diverse Negations from Affirmative Sentences","created":"2024-10-30","cited_by_count":0,"area":null},{"id":"2503.01914","title":"Conceptual Contrastive Edits in Textual and Vision-Language Retrieval","created":"2025-03-01","cited_by_count":0,"area":null},{"id":"2603.19325","title":"Target Concept Tuning Improves Extreme Weather Forecasting","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2605.27249","title":"Gumbel Machine: Counterfactual Student Writing Generation via Gumbel Noise Steering","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2607.13977","title":"Constraint-Aware Counterfactual Editing for Aspect-Based Sentiment Analysis","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2609.30151","title":"Does a model's stated reason for rejecting a candidate do any work?","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}