{"total":104,"rows":[{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2104.14403","title":"Do Feature Attribution Methods Correctly Attribute Features?","created":"2021-04-27","cited_by_count":98,"area":null},{"id":"2103.13084","title":"Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Cases","created":"2021-03-24","cited_by_count":77,"area":null},{"id":"2108.11357","title":"ProoFVer: Natural Logic Theorem Proving for Fact Verification","created":"2021-08-25","cited_by_count":53,"area":null},{"id":"2103.12279","title":"SelfExplain: A Self-Explaining Architecture for Neural Text Classifiers","created":"2021-03-23","cited_by_count":44,"area":null},{"id":"2204.11073","title":"Grad-SAM: Explaining Transformers via Gradient Self-Attention Maps","created":"2022-04-23","cited_by_count":42,"area":null},{"id":"2204.11790","title":"Can Rationalization Improve Robustness?","created":"2022-04-25","cited_by_count":36,"area":null},{"id":"2212.03954","title":"Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning","created":"2022-12-07","cited_by_count":36,"area":null},{"id":"2112.08802","title":"UNIREX: A Unified Learning Framework for Language Model Rationale Extraction","created":"2021-12-16","cited_by_count":32,"area":null},{"id":"2306.02873","title":"DecompX: Explaining Transformers Decisions by Propagating Token Decomposition","created":"2023-06-05","cited_by_count":31,"area":null},{"id":"2105.02657","title":"Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification","created":"2021-05-06","cited_by_count":29,"area":null},{"id":"2110.04392","title":"The Eval4NLP Shared Task on Explainable Quality Estimation: Overview and Results","created":"2021-10-08","cited_by_count":27,"area":null},{"id":"2109.06387","title":"Rationales for Sequential Predictions","created":"2021-09-14","cited_by_count":26,"area":null},{"id":"2112.00071","title":"What to Learn, and How: Toward Effective Learning from Rationales","created":"2021-11-30","cited_by_count":25,"area":null},{"id":"2406.01382","title":"Do Large Language Models Perform the Way People Expect? Measuring the Human Generalization Function","created":"2024-06-03","cited_by_count":24,"area":null},{"id":"2109.11708","title":"Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding","created":"2021-09-24","cited_by_count":23,"area":null},{"id":"2108.12197","title":"Translation Error Detection as Rationale Extraction","created":"2021-08-27","cited_by_count":22,"area":null},{"id":"2210.04982","title":"REV: Information-Theoretic Evaluation of Free-Text Rationales","created":"2022-10-10","cited_by_count":22,"area":null},{"id":"2111.04927","title":"Self-Interpretable Model with TransformationEquivariant Interpretation","created":"2021-11-09","cited_by_count":21,"area":null},{"id":"2203.00056","title":"An Empirical Study on Explanations in Out-of-Domain Settings","created":"2022-02-28","cited_by_count":21,"area":null},{"id":"2204.05426","title":"ProtoTEx: Explaining Model Decisions with Prototype Tensors","created":"2022-04-11","cited_by_count":21,"area":null},{"id":"2309.13391","title":"D-Separation for Causal Self-Explanation","created":"2023-09-23","cited_by_count":21,"area":null},{"id":"2311.02805","title":"Tailoring Self-Rationalizers with Multi-Reward Distillation","created":"2023-11-06","cited_by_count":21,"area":null},{"id":"2105.04837","title":"Rationalization through Concepts","created":"2021-05-11","cited_by_count":19,"area":null},{"id":"2109.04552","title":"SPECTRA: Sparse Structured Text Rationalization","created":"2021-09-09","cited_by_count":19,"area":null},{"id":"2110.10470","title":"Interpreting Deep Learning Models in Natural Language Processing: A Review","created":"2021-10-20","cited_by_count":19,"area":null},{"id":"2203.08991","title":"AdapLeR: Speeding up Inference by Adaptive Length Reduction","created":"2022-03-16","cited_by_count":19,"area":null},{"id":"2306.14115","title":"Towards Trustworthy Explanation: On Causal Rationalization","created":"2023-06-25","cited_by_count":19,"area":null},{"id":"2209.08285","title":"FR: Folded Rationalization with a Unified Encoder","created":"2022-09-17","cited_by_count":18,"area":null},{"id":"2309.07822","title":"CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration","created":"2023-09-14","cited_by_count":17,"area":null},{"id":"2108.13759","title":"Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience","created":"2021-08-31","cited_by_count":16,"area":null},{"id":"2110.07550","title":"The Irrationality of Neural Rationale Models","created":"2021-10-14","cited_by_count":16,"area":null},{"id":"2305.06754","title":"COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP tasks","created":"2023-05-11","cited_by_count":16,"area":null},{"id":"2203.11131","title":"Towards Explainable Evaluation Metrics for Natural Language Generation","created":"2022-03-21","cited_by_count":15,"area":null},{"id":"2212.01060","title":"Exploring Faithful Rationale for Multi-hop Fact Verification via Salience-Aware Graph Learning","created":"2022-12-02","cited_by_count":15,"area":null},{"id":"2312.04103","title":"Enhancing the Rationale-Input Alignment for Self-explaining Rationalization","created":"2023-12-07","cited_by_count":15,"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":"2210.09197","title":"On the Impact of Temporal Concept Drift on Model Explanations","created":"2022-10-17","cited_by_count":14,"area":null},{"id":"2305.13599","title":"Decoupled Rationalization with Asymmetric Learning Rates: A Flexible Lipschitz Restraint","created":"2023-05-23","cited_by_count":14,"area":null},{"id":"2210.07222","title":"Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methods","created":"2022-10-13","cited_by_count":13,"area":null},{"id":"2305.04492","title":"MGR: Multi-generator Based Rationalization","created":"2023-05-08","cited_by_count":12,"area":null},{"id":"2402.00794","title":"ReAGent: A Model-agnostic Feature Attribution Method for Generative Language Models","created":"2024-02-01","cited_by_count":12,"area":null},{"id":"2502.03391","title":"Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient Reasons","created":"2025-02-05","cited_by_count":12,"area":null},{"id":"2109.06896","title":"Decision-Focused Summarization","created":"2021-09-14","cited_by_count":11,"area":null},{"id":"2112.10424","title":"Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction","created":"2021-12-20","cited_by_count":11,"area":null},{"id":"2312.12747","title":"ALMANACS: A Simulatability Benchmark for Language Model Explainability","created":"2023-12-20","cited_by_count":11,"area":null},{"id":"2104.08219","title":"Flexible Instance-Specific Rationalization of NLP Models","created":"2021-04-16","cited_by_count":10,"area":null},{"id":"2201.05177","title":"Making a (Counterfactual) Difference One Rationale at a Time","created":"2022-01-13","cited_by_count":10,"area":null},{"id":"2503.14421","title":"ExDDV: A New Dataset for Explainable Deepfake Detection in Video","created":"2025-03-18","cited_by_count":10,"area":null},{"id":"2203.08788","title":"Are Shortest Rationales the Best Explanations for Human Understanding?","created":"2022-03-16","cited_by_count":8,"area":null},{"id":"2305.07355","title":"ZARA: Improving Few-Shot Self-Rationalization for Small Language Models","created":"2023-05-12","cited_by_count":8,"area":null},{"id":"2306.12181","title":"Feature Interactions Reveal Linguistic Structure in Language Models","created":"2023-06-21","cited_by_count":8,"area":null},{"id":"2402.02754","title":"Focal Modulation Networks for Interpretable Sound Classification","created":"2024-02-05","cited_by_count":8,"area":null},{"id":"2104.08793","title":"SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning","created":"2021-04-18","cited_by_count":7,"area":null},{"id":"2211.03041","title":"Calibration Meets Explanation: A Simple and Effective Approach for Model Confidence Estimates","created":"2022-11-06","cited_by_count":7,"area":null},{"id":"2212.14447","title":"A Theoretical Framework for AI Models Explainability with Application in Biomedicine","created":"2022-12-29","cited_by_count":7,"area":null},{"id":"2605.11161","title":"Interpretability Can Be Actionable","created":"2026-05-11","cited_by_count":7,"area":null},{"id":"2205.12542","title":"ER-Test: Evaluating Explanation Regularization Methods for Language Models","created":"2022-05-25","cited_by_count":6,"area":null},{"id":"2310.16316","title":"Sum-of-Parts: Self-Attributing Neural Networks with End-to-End Learning of Feature Groups","created":"2023-10-25","cited_by_count":6,"area":null},{"id":"2503.06202","title":"Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilization","created":"2025-03-08","cited_by_count":6,"area":null},{"id":"2505.02118","title":"Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets","created":"2025-05-04","cited_by_count":6,"area":null},{"id":"2108.13140","title":"DuTrust: A Sentiment Analysis Dataset for Trustworthiness Evaluation","created":"2021-08-30","cited_by_count":5,"area":null},{"id":"2110.02056","title":"Are Training Resources Insufficient? Predict First Then Explain!","created":"2021-08-29","cited_by_count":5,"area":null},{"id":"2110.07566","title":"Practical Benefits of Feature Feedback Under Distribution Shift","created":"2021-10-14","cited_by_count":5,"area":null},{"id":"2404.03098","title":"Exploring the Trade-off Between Model Performance and Explanation Plausibility of Text Classifiers Using Human Rationales","created":"2024-04-03","cited_by_count":5,"area":null},{"id":"2503.18067","title":"Self-Explaining Neural Networks for Business Process Monitoring","created":"2025-03-23","cited_by_count":5,"area":null},{"id":"2301.06009","title":"Rationalizing Predictions by Adversarial Information Calibration","created":"2023-01-15","cited_by_count":4,"area":null},{"id":"2305.16128","title":"Give Me More Details: Improving Fact-Checking with Latent Retrieval","created":"2023-05-25","cited_by_count":4,"area":null},{"id":"2312.17591","title":"Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training","created":"2023-12-29","cited_by_count":4,"area":null},{"id":"2502.13991","title":"Learning to Discover Regulatory Elements for Gene Expression Prediction","created":"2025-02-19","cited_by_count":4,"area":null},{"id":"2504.02911","title":"Noiser: Bounded Input Perturbations for Attributing Large Language Models","created":"2025-04-03","cited_by_count":4,"area":null},{"id":"2210.07469","title":"StyLEx: Explaining Style Using Human Lexical Annotations","created":"2022-10-14","cited_by_count":3,"area":null},{"id":"2302.00102","title":"Towards Detecting Harmful Agendas in News Articles","created":"2023-01-31","cited_by_count":3,"area":null},{"id":"2305.09400","title":"Consistent Multi-Granular Rationale Extraction for Explainable Multi-hop Fact Verification","created":"2023-05-16","cited_by_count":3,"area":null},{"id":"2305.17534","title":"Unsupervised Selective Rationalization with Noise Injection","created":"2023-05-27","cited_by_count":3,"area":null},{"id":"2411.02664","title":"Explanations that reveal all through the definition of encoding","created":"2024-11-04","cited_by_count":3,"area":null},{"id":"2511.07065","title":"Aligning Attention with Human Rationales for Self-Explaining Hate Speech Detection","created":"2025-11-10","cited_by_count":3,"area":null},{"id":"2103.14919","title":"You Can Do Better! If You Elaborate the Reason When Making Prediction","created":"2021-03-27","cited_by_count":2,"area":null},{"id":"2104.07894","title":"Faithful and Plausible Explanations of Medical Code Predictions","created":"2021-04-16","cited_by_count":2,"area":null},{"id":"2110.07686","title":"Making Document-Level Information Extraction Right for the Right Reasons","created":"2021-10-14","cited_by_count":2,"area":null},{"id":"2206.02761","title":"Dual Decomposition of Convex Optimization Layers for Consistent Attention in Medical Images","created":"2022-06-06","cited_by_count":2,"area":null},{"id":"2208.09316","title":"UKP-SQuARE v2: Explainability and Adversarial Attacks for Trustworthy QA","created":"2022-08-19","cited_by_count":2,"area":null},{"id":"2212.00851","title":"SOLD: Sinhala Offensive Language Dataset","created":"2022-12-01","cited_by_count":2,"area":null},{"id":"2310.17010","title":"This Reads Like That: Deep Learning for Interpretable Natural Language Processing","created":"2023-10-25","cited_by_count":2,"area":null},{"id":"2506.07446","title":"Fact in Fragments: Deconstructing Complex Claims via LLM-based Atomic Fact Extraction and Verification","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2512.05373","title":"Text Rationalization for Robust Causal Effect Estimation","created":"2025-12-05","cited_by_count":2,"area":null},{"id":"2109.04726","title":"AutoTriggER: Label-Efficient and Robust Named Entity Recognition with Auxiliary Trigger Extraction","created":"2021-09-10","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":"2303.06876","title":"A Test Statistic Estimation-based Approach for Establishing Self-interpretable CNN-based Binary Classifiers","created":"2023-03-13","cited_by_count":1,"area":null},{"id":"2303.07991","title":"Finding the Needle in a Haystack: Unsupervised Rationale Extraction from Long Text Classifiers","created":"2023-03-14","cited_by_count":1,"area":null},{"id":"2210.11805","title":"Robustifying Sentiment Classification by Maximally Exploiting Few Counterfactuals","created":"2022-10-21","cited_by_count":0,"area":null},{"id":"2211.08369","title":"Easy to Decide, Hard to Agree: Reducing Disagreements Between Saliency Methods","created":"2022-11-15","cited_by_count":0,"area":null},{"id":"2305.19748","title":"UKP-SQuARE: An Interactive Tool for Teaching Question Answering","created":"2023-05-31","cited_by_count":0,"area":null},{"id":"2308.15232","title":"Classification-Aware Neural Topic Model Combined With Interpretable Analysis -- For Conflict Classification","created":"2023-08-29","cited_by_count":0,"area":null},{"id":"2310.19268","title":"Moral Sparks in Social Media Narratives","created":"2023-10-30","cited_by_count":0,"area":null},{"id":"2406.05251","title":"Automated Trustworthiness Testing for Machine Learning Classifiers","created":"2024-06-07","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":"2411.04557","title":"Pruning Literals for Highly Efficient Explainability at Word Level","created":"2024-11-07","cited_by_count":0,"area":null},{"id":"2506.07168","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","created":"2025-06-08","cited_by_count":0,"area":null},{"id":"2601.22531","title":"Learn from A Rationalist: Distilling Intermediate Interpretable Rationales","created":"2026-01-30","cited_by_count":0,"area":null}],"next_cursor":"100"}