{"total":87,"rows":[{"id":"2309.16042","title":"Towards Best Practices of Activation Patching in Language Models: Metrics and Methods","created":"2023-09-27","cited_by_count":359,"area":"mechinterp"},{"id":"2201.08164","title":"From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI","created":"2022-01-20","cited_by_count":302,"area":null},{"id":"2404.15255","title":"How to use and interpret activation patching","created":"2024-04-23","cited_by_count":214,"area":null},{"id":"2211.10154","title":"CRAFT: Concept Recursive Activation FacTorization for Explainability","created":"2022-11-17","cited_by_count":178,"area":null},{"id":"2202.06861","title":"Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond","created":"2022-02-14","cited_by_count":171,"area":null},{"id":"2502.12892","title":"Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models","created":"2025-02-18","cited_by_count":73,"area":"mechinterp"},{"id":"2207.04154","title":"TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversations","created":"2022-07-08","cited_by_count":66,"area":null},{"id":"2202.00734","title":"Framework for Evaluating Faithfulness of Local Explanations","created":"2022-02-01","cited_by_count":55,"area":null},{"id":"2308.06248","title":"FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods","created":"2023-08-11","cited_by_count":50,"area":null},{"id":"2201.12114","title":"Rethinking Attention-Model Explainability through Faithfulness Violation Test","created":"2022-01-28","cited_by_count":43,"area":null},{"id":"2306.02109","title":"Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency","created":"2023-06-03","cited_by_count":42,"area":null},{"id":"2202.07728","title":"Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis","created":"2022-02-15","cited_by_count":38,"area":null},{"id":"2401.06654","title":"Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarks","created":"2024-01-12","cited_by_count":28,"area":null},{"id":"2409.09951","title":"Optimal ablation for interpretability","created":"2024-09-16","cited_by_count":25,"area":null},{"id":"2211.05667","title":"What Makes a Good Explanation?: A Harmonized View of Properties of Explanations","created":"2022-11-10","cited_by_count":22,"area":null},{"id":"2401.08552","title":"Explaining Time Series via Contrastive and Locally Sparse Perturbations","created":"2024-01-16","cited_by_count":22,"area":null},{"id":"2401.02452","title":"The Compute Divide in Machine Learning: A Threat to Academic Contribution and Scrutiny?","created":"2024-01-04","cited_by_count":20,"area":null},{"id":"2404.01415","title":"On the Faithfulness of Vision Transformer Explanations","created":"2024-04-01","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":"2410.02970","title":"F-Fidelity: A Robust Framework for Faithfulness Evaluation of Explainable AI","created":"2024-10-03","cited_by_count":18,"area":null},{"id":"2310.01820","title":"Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networks","created":"2023-10-03","cited_by_count":17,"area":null},{"id":"2307.14517","title":"The Co-12 Recipe for Evaluating Interpretable Part-Prototype Image Classifiers","created":"2023-07-26","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":"2207.05566","title":"BASED-XAI: Breaking Ablation Studies Down for Explainable Artificial Intelligence","created":"2022-07-12","cited_by_count":13,"area":null},{"id":"2206.11212","title":"VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives","created":"2022-06-22","cited_by_count":12,"area":"lr"},{"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":"2402.03485","title":"Attention Meets Post-hoc Interpretability: A Mathematical Perspective","created":"2024-02-05","cited_by_count":11,"area":null},{"id":"2407.19897","title":"BEExAI: Benchmark to Evaluate Explainable AI","created":"2024-07-29","cited_by_count":11,"area":null},{"id":"2408.03915","title":"Hard to Explain: On the Computational Hardness of In-Distribution Model Interpretation","created":"2024-08-07","cited_by_count":11,"area":null},{"id":"2503.11302","title":"Are formal and functional linguistic mechanisms dissociated in language models?","created":"2025-03-14","cited_by_count":11,"area":null},{"id":"2308.14272","title":"Goodhart's Law Applies to NLP's Explanation Benchmarks","created":"2023-08-28","cited_by_count":10,"area":null},{"id":"2408.08137","title":"Normalized AOPC: Fixing Misleading Faithfulness Metrics for Feature Attribution Explainability","created":"2024-08-15","cited_by_count":10,"area":null},{"id":"2504.13787","title":"Probabilistic Stability Guarantees for Feature Attributions","created":"2025-04-18","cited_by_count":9,"area":null},{"id":"2305.15734","title":"On the Impact of Knowledge Distillation for Model Interpretability","created":"2023-05-25","cited_by_count":8,"area":"distill"},{"id":"2407.11910","title":"Benchmarking the Attribution Quality of Vision Models","created":"2024-07-16","cited_by_count":8,"area":null},{"id":"2411.02470","title":"Benchmarking XAI Explanations with Human-Aligned Evaluations","created":"2024-11-04","cited_by_count":8,"area":"alignment"},{"id":"2206.06029","title":"Mediators: Conversational Agents Explaining NLP Model Behavior","created":"2022-06-13","cited_by_count":7,"area":null},{"id":"2205.13789","title":"A Sea of Words: An In-Depth Analysis of Anchors for Text Data","created":"2022-05-27","cited_by_count":6,"area":null},{"id":"2206.06854","title":"On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective","created":"2022-06-14","cited_by_count":6,"area":null},{"id":"2508.05430","title":"Explaining Similarity in Vision-Language Encoders with Weighted Banzhaf Interactions","created":"2025-08-07","cited_by_count":6,"area":"mllm"},{"id":"2110.11929","title":"Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models?","created":"2021-10-22","cited_by_count":5,"area":null},{"id":"2203.12000","title":"Text Transformations in Contrastive Self-Supervised Learning: A Review","created":"2022-03-22","cited_by_count":5,"area":null},{"id":"2308.05219","title":"Decoding Layer Saliency in Language Transformers","created":"2023-08-09","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":"2406.04612","title":"Faithful and Accurate Self-Attention Attribution for Message Passing Neural Networks via the Computation Tree Viewpoint","created":"2024-06-07","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":"2601.20815","title":"GNN Explanations that do not Explain and How to find Them","created":"2026-01-28","cited_by_count":5,"area":null},{"id":"2606.25234","title":"Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds","created":"2026-06-23","cited_by_count":5,"area":null},{"id":"2305.19998","title":"Efficient Shapley Values Estimation by Amortization for Text Classification","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2406.18334","title":"Efficient and Accurate Explanation Estimation with Distribution Compression","created":"2024-06-26","cited_by_count":4,"area":null},{"id":"2412.05592","title":"From Flexibility to Manipulation: The Slippery Slope of XAI Evaluation","created":"2024-12-07","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":"2207.11231","title":"Learning Unsupervised Hierarchies of Audio Concepts","created":"2022-07-21","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":"2511.10439","title":"Improving Perturbation-based Explanations by Understanding the Role of Uncertainty Calibration","created":"2025-11-13","cited_by_count":3,"area":null},{"id":"2311.01605","title":"Faithful and Robust Local Interpretability for Textual Predictions","created":"2023-10-30","cited_by_count":2,"area":null},{"id":"2404.14996","title":"CA-Stream: Attention-based pooling for interpretable image recognition","created":"2024-04-23","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":"2504.10833","title":"Measuring the (Un)Faithfulness of Concept-Based Explanations","created":"2025-04-15","cited_by_count":2,"area":null},{"id":"2505.00802","title":"Explanations as Bias Detectors: A Critical Study of Local Post-hoc XAI Methods for Fairness Exploration","created":"2025-05-01","cited_by_count":2,"area":null},{"id":"2605.16222","title":"Artificial Aphasias in Lesioned Language Models","created":"2026-05-15","cited_by_count":2,"area":null},{"id":"2303.08806","title":"Understanding Post-hoc Explainers: The Case of Anchors","created":"2023-03-15","cited_by_count":1,"area":null},{"id":"2310.06654","title":"Evaluating Explanation Methods for Vision-and-Language Navigation","created":"2023-10-10","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":"2504.13140","title":"PCBEAR: Pose Concept Bottleneck for Explainable Action Recognition","created":"2025-04-17","cited_by_count":1,"area":null},{"id":"2510.21884","title":"Support-Contra Asymmetry in LLM Explanations","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2512.11433","title":"Back to the Baseline: Examining Baseline Effects on Explainability Metrics","created":"2025-12-12","cited_by_count":1,"area":null},{"id":"2601.04398","title":"Interpreting Transformers Through Attention Head Intervention","created":"2026-01-07","cited_by_count":1,"area":"mechinterp"},{"id":"2603.04831","title":"Missingness Bias Calibration in Feature Attribution Explanations","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2206.00192","title":"Order-sensitive Shapley Values for Evaluating Conceptual Soundness of NLP Models","created":"2022-06-01","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":"2212.12374","title":"Relational Local Explanations","created":"2022-12-23","cited_by_count":0,"area":null},{"id":"2407.06339","title":"Noise-Free Explanation for Driving Action Prediction","created":"2024-07-08","cited_by_count":0,"area":null},{"id":"2506.19630","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","created":"2025-06-24","cited_by_count":0,"area":null},{"id":"2512.11108","title":"Explanation Bias is a Product: Revealing the Hidden Lexical and Position Preferences in Post-Hoc Feature Attribution","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2603.18579","title":"ICE: Intervention-Consistent Explanation Evaluation with Statistical Grounding for LLMs","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2604.14433","title":"Zero-Ablation Overstates Register Content Dependence in DINO Vision Transformers","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2606.10877","title":"XtrAIn: Training-Guided Occlusion for Feature Attribution","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.21564","title":"LIG: Layer-wise Integrated Gradients for Within-Layer Flow Analysis in Transformers","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.09306","title":"Exposure is not manifestation: measurement target and output resolution jointly determine which behavioural-faithfulness evaluator wins","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.28386","title":"Explaining Image Similarity with Automatically Extracted Concept Activation Vectors","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.25028","title":"Behind the [MASK]: Disentangling Representation and Faithfulness in DAPF-Based Dementia Detection","created":"2026-08-25","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},{"id":"2609.37594","title":"XU-RS: Explaining Credal Width in Random-Set Language Models","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39243","title":"Right Answer, Wrong Mechanism: Detecting Pernicious Divergence in Causal Interventions","created":"2026-09-30","cited_by_count":0,"area":"mechinterp"},{"id":"2610.12493","title":"Faithfulness Without Anchors: A Position Paper on the Structural Misalignments of Explainable AI Faithfulness Metrics for Feature Importance","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}