{"total":190,"rows":[{"id":"2505.05410","title":"Reasoning Models Don't Always Say What They Think","created":"2025-05-08","cited_by_count":415,"area":"lr"},{"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":"2101.00288","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","created":"2021-01-01","cited_by_count":222,"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":"2102.13076","title":"Benchmarking and Survey of Explanation Methods for Black Box Models","created":"2021-02-25","cited_by_count":136,"area":null},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2110.10790","title":"Human-Centered Explainable AI (XAI): From Algorithms to User Experiences","created":"2021-10-20","cited_by_count":123,"area":null},{"id":"2212.06823","title":"Explanations Can Reduce Overreliance on AI Systems During Decision-Making","created":"2022-12-13","cited_by_count":111,"area":null},{"id":"2306.07304","title":"A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation","created":"2023-06-11","cited_by_count":109,"area":null},{"id":"2112.03184","title":"HIVE: Evaluating the Human Interpretability of Visual Explanations","created":"2021-12-06","cited_by_count":105,"area":null},{"id":"2202.00449","title":"A Consistent and Efficient Evaluation Strategy for Attribution Methods","created":"2022-02-01","cited_by_count":102,"area":null},{"id":"2112.04417","title":"What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods","created":"2021-12-06","cited_by_count":98,"area":null},{"id":"2202.10419","title":"Interpreting Language Models with Contrastive Explanations","created":"2022-02-21","cited_by_count":92,"area":null},{"id":"2105.14944","title":"The effectiveness of feature attribution methods and its correlation with automatic evaluation scores","created":"2021-05-31","cited_by_count":88,"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":"2112.11471","title":"Towards a Science of Human-AI Decision Making: A Survey of Empirical Studies","created":"2021-12-21","cited_by_count":86,"area":null},{"id":"2210.11584","title":"Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations","created":"2022-10-20","cited_by_count":85,"area":null},{"id":"2307.08678","title":"Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations","created":"2023-07-17","cited_by_count":85,"area":null},{"id":"2205.15612","title":"GlanceNets: Interpretabile, Leak-proof Concept-based Models","created":"2022-05-31","cited_by_count":73,"area":null},{"id":"2301.07255","title":"Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations","created":"2023-01-18","cited_by_count":73,"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":"2301.05809","title":"Who Should I Trust: AI or Myself? Leveraging Human and AI Correctness Likelihood to Promote Appropriate Trust in AI-Assisted Decision-Making","created":"2023-01-14","cited_by_count":67,"area":null},{"id":"2502.03714","title":"Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment","created":"2025-02-06","cited_by_count":62,"area":"mechinterp"},{"id":"2205.14140","title":"CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior","created":"2022-05-27","cited_by_count":55,"area":null},{"id":"2205.15769","title":"Concept-level Debugging of Part-Prototype Networks","created":"2022-05-31","cited_by_count":52,"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":"2206.10847","title":"Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AI","created":"2022-06-22","cited_by_count":40,"area":null},{"id":"2201.06028","title":"Natural Language Deduction through Search over Statement Compositions","created":"2022-01-16","cited_by_count":35,"area":null},{"id":"2202.10553","title":"Guidelines and Evaluation of Clinical Explainable AI in Medical Image Analysis","created":"2022-02-16","cited_by_count":35,"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":"2110.08412","title":"Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining","created":"2021-10-15","cited_by_count":31,"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":"2104.08782","title":"On the Sensitivity and Stability of Model Interpretations in NLP","created":"2021-04-18","cited_by_count":30,"area":null},{"id":"2111.11297","title":"Teaching Humans When To Defer to a Classifier via Exemplars","created":"2021-11-22","cited_by_count":29,"area":null},{"id":"2205.05126","title":"A Meta-Analysis of the Utility of Explainable Artificial Intelligence in Human-AI Decision-Making","created":"2022-05-10","cited_by_count":29,"area":null},{"id":"2106.12447","title":"How Well do Feature Visualizations Support Causal Understanding of CNN Activations?","created":"2021-06-23","cited_by_count":28,"area":null},{"id":"2211.12380","title":"OCTET: Object-aware Counterfactual Explanations","created":"2022-11-22","cited_by_count":28,"area":null},{"id":"2401.15356","title":"A Decision Theoretic Framework for Measuring AI Reliance","created":"2024-01-27","cited_by_count":28,"area":null},{"id":"2306.06805","title":"Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization","created":"2023-06-11","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":"2401.13986","title":"Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning","created":"2024-01-25","cited_by_count":26,"area":null},{"id":"2204.05426","title":"ProtoTEx: Explaining Model Decisions with Prototype Tensors","created":"2022-04-11","cited_by_count":21,"area":null},{"id":"2302.10894","title":"Red Teaming Deep Neural Networks with Feature Synthesis Tools","created":"2023-02-08","cited_by_count":21,"area":"safety"},{"id":"2405.06800","title":"LLM-Generated Black-box Explanations Can Be Adversarially Helpful","created":"2024-05-10","cited_by_count":21,"area":null},{"id":"2506.22777","title":"Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning","created":"2025-06-28","cited_by_count":21,"area":"lr"},{"id":"2102.11115","title":"Probing Multimodal Embeddings for Linguistic Properties: the Visual-Semantic Case","created":"2021-02-22","cited_by_count":20,"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":"2110.07586","title":"Can Explanations Be Useful for Calibrating Black Box Models?","created":"2021-10-14","cited_by_count":20,"area":null},{"id":"2202.04092","title":"Machine Explanations and Human Understanding","created":"2022-02-08","cited_by_count":20,"area":null},{"id":"2203.06487","title":"Evaluating Explainable AI on a Multi-Modal Medical Imaging Task: Can Existing Algorithms Fulfill Clinical Requirements?","created":"2022-03-12","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":"2311.01007","title":"Effective Human-AI Teams via Learned Natural Language Rules and Onboarding","created":"2023-11-02","cited_by_count":20,"area":null},{"id":"2206.02256","title":"Use-Case-Grounded Simulations for Explanation Evaluation","created":"2022-06-05","cited_by_count":19,"area":null},{"id":"2501.12868","title":"As Confidence Aligns: Exploring the Effect of AI Confidence on Human Self-confidence in Human-AI Decision Making","created":"2025-01-22","cited_by_count":19,"area":null},{"id":"2406.09264","title":"Position: Towards Bidirectional Human-AI Alignment","created":"2024-06-13","cited_by_count":18,"area":"alignment"},{"id":"2412.12386","title":"Interpretable LLM-based Table Question Answering","created":"2024-12-16","cited_by_count":18,"area":null},{"id":"2106.04631","title":"On the Lack of Robust Interpretability of Neural Text Classifiers","created":"2021-06-08","cited_by_count":17,"area":null},{"id":"2602.20710","title":"Counterfactual Simulation Training for Chain-of-Thought Faithfulness","created":"2026-02-24","cited_by_count":17,"area":"lr"},{"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":"2306.09299","title":"Can Language Models Teach Weaker Agents? Teacher Explanations Improve Students via Personalization","created":"2023-06-15","cited_by_count":16,"area":"agents"},{"id":"2105.10172","title":"Explainable Machine Learning with Prior Knowledge: An Overview","created":"2021-05-21","cited_by_count":15,"area":null},{"id":"2106.01354","title":"multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoning","created":"2021-06-02","cited_by_count":15,"area":null},{"id":"2109.01962","title":"Counterfactual Evaluation for Explainable AI","created":"2021-09-05","cited_by_count":15,"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":"2205.00130","title":"ExSum: From Local Explanations to Model Understanding","created":"2022-04-30","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":"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":"2209.10492","title":"Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees","created":"2022-09-21","cited_by_count":14,"area":null},{"id":"2401.07058","title":"Does More Advice Help? The Effects of Second Opinions in AI-Assisted Decision Making","created":"2024-01-13","cited_by_count":14,"area":null},{"id":"2106.15355","title":"On the Interaction of Belief Bias and Explanations","created":"2021-06-29","cited_by_count":13,"area":null},{"id":"2206.11083","title":"Investigating the Benefits of Free-Form Rationales","created":"2022-05-25","cited_by_count":13,"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":"2304.11218","title":"Explainability in AI Policies: A Critical Review of Communications, Reports, Regulations, and Standards in the EU, US, and UK","created":"2023-04-20","cited_by_count":13,"area":null},{"id":"2105.02357","title":"Explainable Artificial Intelligence for Human Decision-Support System in Medical Domain","created":"2021-05-05","cited_by_count":12,"area":null},{"id":"2211.00614","title":"Natural Language Deduction with Incomplete Information","created":"2022-11-01","cited_by_count":12,"area":null},{"id":"2502.18848","title":"A Causal Lens for Evaluating Faithfulness Metrics","created":"2025-02-26","cited_by_count":12,"area":null},{"id":"2108.13961","title":"Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools","created":"2021-08-31","cited_by_count":11,"area":null},{"id":"2310.05592","title":"InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations","created":"2023-10-09","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":"2502.15886","title":"A Close Look at Decomposition-based XAI-Methods for Transformer Language Models","created":"2025-02-21","cited_by_count":11,"area":null},{"id":"2602.17053","title":"RFEval: Benchmarking Reasoning Faithfulness under Counterfactual Reasoning Intervention in Large Reasoning Models","created":"2026-02-19","cited_by_count":11,"area":"lr"},{"id":"2104.04075","title":"Towards a Rigorous Evaluation of Explainability for Multivariate Time Series","created":"2021-04-06","cited_by_count":10,"area":null},{"id":"2205.08452","title":"A Psychological Theory of Explainability","created":"2022-05-17","cited_by_count":10,"area":null},{"id":"2207.00779","title":"FRAME: Evaluating Rationale-Label Consistency Metrics for Free-Text Rationales","created":"2022-07-02","cited_by_count":10,"area":null},{"id":"2411.10461","title":"Utilizing Human Behavior Modeling to Manipulate Explanations in AI-Assisted Decision Making: The Good, the Bad, and the Scary","created":"2024-11-02","cited_by_count":10,"area":null},{"id":"2602.06218","title":"Cross-Modal Redundancy and the Geometry of Vision-Language Embeddings","created":"2026-02-05","cited_by_count":10,"area":"mllm"},{"id":"2204.07693","title":"Calibrating Trust of Multi-Hop Question Answering Systems with Decompositional Probes","created":"2022-04-16","cited_by_count":9,"area":"lr"},{"id":"2207.06897","title":"Beware the Rationalization Trap! When Language Model Explainability Diverges from our Mental Models of Language","created":"2022-07-14","cited_by_count":9,"area":null},{"id":"2501.05855","title":"ConSim: Measuring Concept-Based Explanations' Effectiveness with Automated Simulatability","created":"2025-01-10","cited_by_count":9,"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":"2409.12809","title":"Don't be Fooled: The Misinformation Effect of Explanations in Human-AI Collaboration","created":"2024-09-19","cited_by_count":8,"area":null},{"id":"2410.22239","title":"DISCERN: Decoding Systematic Errors in Natural Language for Text Classifiers","created":"2024-10-29","cited_by_count":8,"area":null},{"id":"2502.18816","title":"Grad-ECLIP: Gradient-based Visual and Textual Explanations for CLIP","created":"2025-02-26","cited_by_count":8,"area":"mllm"},{"id":"2602.14869","title":"Concept Influence: Leveraging Interpretability to Improve Performance and Efficiency in Training Data Attribution","created":"2026-02-16","cited_by_count":8,"area":"mechinterp"},{"id":"2107.02033","title":"Quality Metrics for Transparent Machine Learning With and Without Humans In the Loop Are Not Correlated","created":"2021-07-01","cited_by_count":7,"area":null},{"id":"2206.06029","title":"Mediators: Conversational Agents Explaining NLP Model Behavior","created":"2022-06-13","cited_by_count":7,"area":null},{"id":"2505.10399","title":"Evaluating Model Explanations without Ground Truth","created":"2025-05-15","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":"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}],"next_cursor":"100"}