{"total":79,"rows":[{"id":"2212.07919","title":"ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning","created":"2022-12-15","cited_by_count":177,"area":"lr"},{"id":"2205.03401","title":"The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning","created":"2022-05-06","cited_by_count":169,"area":"lr"},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"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":"2104.14403","title":"Do Feature Attribution Methods Correctly Attribute Features?","created":"2021-04-27","cited_by_count":98,"area":null},{"id":"2106.00786","title":"The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations","created":"2021-06-01","cited_by_count":87,"area":null},{"id":"2101.05307","title":"Explainability of deep vision-based autonomous driving systems: Review and challenges","created":"2021-01-13","cited_by_count":80,"area":null},{"id":"2103.01378","title":"Contrastive Explanations for Model Interpretability","created":"2021-03-02","cited_by_count":75,"area":null},{"id":"2202.00734","title":"Framework for Evaluating Faithfulness of Local Explanations","created":"2022-02-01","cited_by_count":55,"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":"2305.07722","title":"In Search of Verifiability: Explanations Rarely Enable Complementary Performance in AI-Advised Decision Making","created":"2023-05-12","cited_by_count":50,"area":null},{"id":"2110.13880","title":"Understanding Interlocking Dynamics of Cooperative Rationalization","created":"2021-10-26","cited_by_count":36,"area":null},{"id":"2105.08621","title":"Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networks","created":"2021-05-18","cited_by_count":35,"area":null},{"id":"2106.01087","title":"Is Sparse Attention more Interpretable?","created":"2021-06-02","cited_by_count":31,"area":null},{"id":"2106.15231","title":"Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment Analysis","created":"2021-06-29","cited_by_count":30,"area":null},{"id":"2202.02838","title":"Aligning Eyes between Humans and Deep Neural Network through Interactive Attention Alignment","created":"2022-02-06","cited_by_count":27,"area":null},{"id":"2112.09669","title":"Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations","created":"2021-12-17","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":"2201.11569","title":"Human Interpretation of Saliency-based Explanation Over Text","created":"2022-01-27","cited_by_count":25,"area":null},{"id":"2410.09087","title":"Mechanistic?","created":"2024-10-07","cited_by_count":25,"area":"mechinterp"},{"id":"2106.13876","title":"Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations","created":"2021-06-25","cited_by_count":24,"area":null},{"id":"2402.10532","title":"Properties and Challenges of LLM-Generated Explanations","created":"2024-02-16","cited_by_count":24,"area":null},{"id":"2206.13413","title":"RES: A Robust Framework for Guiding Visual Explanation","created":"2022-06-27","cited_by_count":22,"area":null},{"id":"2104.04515","title":"Connecting Attributions and QA Model Behavior on Realistic Counterfactuals","created":"2021-04-09","cited_by_count":20,"area":null},{"id":"2204.10810","title":"Learning to Scaffold: Optimizing Model Explanations for Teaching","created":"2022-04-22","cited_by_count":20,"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":"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":"2501.15638","title":"A Comprehensive Survey on Self-Interpretable Neural Networks","created":"2025-01-26","cited_by_count":18,"area":null},{"id":"2312.01279","title":"TextGenSHAP: Scalable Post-hoc Explanations in Text Generation with Long Documents","created":"2023-12-03","cited_by_count":17,"area":"lr"},{"id":"2110.07550","title":"The Irrationality of Neural Rationale Models","created":"2021-10-14","cited_by_count":16,"area":null},{"id":"2201.11239","title":"Diagnosing AI Explanation Methods with Folk Concepts of Behavior","created":"2022-01-27","cited_by_count":15,"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":"2204.08892","title":"A survey on improving NLP models with human explanations","created":"2022-04-19","cited_by_count":15,"area":null},{"id":"2306.13041","title":"Towards Explainable Evaluation Metrics for Machine Translation","created":"2023-06-22","cited_by_count":15,"area":null},{"id":"2410.14155","title":"Towards Faithful Natural Language Explanations: A Study Using Activation Patching in Large Language Models","created":"2024-10-18","cited_by_count":14,"area":"mechinterp"},{"id":"2206.11083","title":"Investigating the Benefits of Free-Form Rationales","created":"2022-05-25","cited_by_count":13,"area":null},{"id":"2402.13725","title":"Sparse and Structured Hopfield Networks","created":"2024-02-21","cited_by_count":13,"area":null},{"id":"2106.04753","title":"On Sample Based Explanation Methods for NLP:Efficiency, Faithfulness, and Semantic Evaluation","created":"2021-06-09","cited_by_count":12,"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":"2205.13042","title":"How explainable are adversarially-robust CNNs?","created":"2022-05-25","cited_by_count":9,"area":null},{"id":"2402.02933","title":"Intrinsic User-Centric Interpretability through Global Mixture of Experts","created":"2024-02-05","cited_by_count":9,"area":"moe"},{"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":"2310.14198","title":"QA-NatVer: Question Answering for Natural Logic-based Fact Verification","created":"2023-10-22","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":"2503.23899","title":"Rubrik's Cube: Testing a New Rubric for Evaluating Explanations on the CUBE dataset","created":"2025-03-31","cited_by_count":8,"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":"2311.01732","title":"Proto-lm: A Prototypical Network-Based Framework for Built-in Interpretability in Large Language Models","created":"2023-11-03","cited_by_count":7,"area":"mechinterp"},{"id":"2605.11161","title":"Interpretability Can Be Actionable","created":"2026-05-11","cited_by_count":7,"area":null},{"id":"2109.03756","title":"Diagnostics-Guided Explanation Generation","created":"2021-09-08","cited_by_count":6,"area":null},{"id":"2110.08887","title":"Schr\\\"odinger's Tree -- On Syntax and Neural Language Models","created":"2021-10-17","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":"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":"2110.02058","title":"Interactively Providing Explanations for Transformer Language Models","created":"2021-09-02","cited_by_count":4,"area":null},{"id":"2502.12992","title":"B-cos LM: Efficiently Transforming Pre-trained Language Models for Improved Explainability","created":"2025-02-18","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":"2305.17534","title":"Unsupervised Selective Rationalization with Noise Injection","created":"2023-05-27","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":"2411.01093","title":"TabVer: Tabular Fact Verification with Natural Logic","created":"2024-11-02","cited_by_count":3,"area":"lr"},{"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":"2308.14115","title":"Situated Natural Language Explanations","created":"2023-08-27","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":"2409.17774","title":"Faithfulness and the Notion of Adversarial Sensitivity in NLP Explanations","created":"2024-09-26","cited_by_count":2,"area":null},{"id":"2501.03182","title":"Boosting Explainability through Selective Rationalization in Pre-trained Language Models","created":"2025-01-03","cited_by_count":2,"area":null},{"id":"2506.19113","title":"Argument-Based Consistency in Toxicity Explanations of LLMs","created":"2025-06-23","cited_by_count":2,"area":null},{"id":"2511.04070","title":"T-FIX: Text-Based Explanations with Features Interpretable to eXperts","created":"2025-11-06","cited_by_count":2,"area":null},{"id":"2307.02094","title":"DARE: Towards Robust Text Explanations in Biomedical and Healthcare Applications","created":"2023-07-05","cited_by_count":1,"area":null},{"id":"2407.11778","title":"Local Feature Selection without Label or Feature Leakage for Interpretable Machine Learning Predictions","created":"2024-07-16","cited_by_count":1,"area":null},{"id":"2407.16693","title":"Explanation Regularisation through the Lens of Attributions","created":"2024-07-23","cited_by_count":1,"area":null},{"id":"2412.20798","title":"Reconciling Privacy and Explainability in High-Stakes: A Systematic Inquiry","created":"2024-12-30","cited_by_count":1,"area":null},{"id":"2608.29942","title":"Influence Is Not Authority: When Causal Guardrail Signals Make Legitimate Tool Use Look Like an Attack in Tool-Using LLM Agents","created":"2026-08-30","cited_by_count":1,"area":"agents"},{"id":"2206.03491","title":"EiX-GNN : Concept-level eigencentrality explainer for graph neural networks","created":"2022-06-07","cited_by_count":0,"area":null},{"id":"2206.11126","title":"Explanation-based Counterfactual Retraining(XCR): A Calibration Method for Black-box Models","created":"2022-06-22","cited_by_count":0,"area":null},{"id":"2207.04969","title":"From Correlation to Causation: Formalizing Interpretable Machine Learning as a Statistical Process","created":"2022-07-11","cited_by_count":0,"area":null},{"id":"2211.07982","title":"Evaluating the Faithfulness of Saliency-based Explanations for Deep Learning Models for Temporal Colour Constancy","created":"2022-11-15","cited_by_count":0,"area":null},{"id":"2212.07126","title":"Explainability of Text Processing and Retrieval Methods: A Survey","created":"2022-12-14","cited_by_count":0,"area":null},{"id":"2607.15957","title":"From Plausible to Actionable: A Position on LLM Self-Explanations","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2609.32934","title":"The Impact of Stochasticity on the Rashomon Effect in Machine Learning","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}