{"total":599,"rows":[{"id":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122,"area":"lr"},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940,"area":"lr"},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724,"area":"mechinterp"},{"id":"2307.13702","title":"Measuring Faithfulness in Chain-of-Thought Reasoning","created":"2023-07-17","cited_by_count":703,"area":"lr"},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2505.05410","title":"Reasoning Models Don't Always Say What They Think","created":"2025-05-08","cited_by_count":415,"area":"lr"},{"id":"2503.11926","title":"Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation","created":"2025-03-14","cited_by_count":384,"area":"lr"},{"id":"2108.11896","title":"A Survey on Automated Fact-Checking","created":"2021-08-26","cited_by_count":378,"area":null},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"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":"2203.11147","title":"Teaching language models to support answers with verified quotes","created":"2022-03-21","cited_by_count":292,"area":null},{"id":"2301.13379","title":"Faithful Chain-of-Thought Reasoning","created":"2023-01-31","cited_by_count":288,"area":"lr"},{"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":"2303.02536","title":"Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations","created":"2023-03-05","cited_by_count":209,"area":null},{"id":"2301.04709","title":"Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability","created":"2023-01-11","cited_by_count":205,"area":"mechinterp"},{"id":"2109.00725","title":"Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond","created":"2021-09-02","cited_by_count":178,"area":null},{"id":"2503.08679","title":"Chain-of-Thought Reasoning In The Wild Is Not Always Faithful","created":"2025-03-11","cited_by_count":170,"area":"lr"},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156,"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":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"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":"2306.01941","title":"AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap","created":"2023-06-02","cited_by_count":123,"area":null},{"id":"2103.10689","title":"Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond","created":"2021-03-19","cited_by_count":118,"area":null},{"id":"2407.02646","title":"A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models","created":"2024-07-02","cited_by_count":118,"area":"mechinterp"},{"id":"2110.06674","title":"Truthful AI: Developing and governing AI that does not lie","created":"2021-10-13","cited_by_count":113,"area":null},{"id":"2112.00826","title":"Inducing Causal Structure for Interpretable Neural Networks","created":"2021-12-01","cited_by_count":110,"area":null},{"id":"2402.13950","title":"Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning","created":"2024-02-21","cited_by_count":110,"area":"lr"},{"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":"2307.11768","title":"Question Decomposition Improves the Faithfulness of Model-Generated Reasoning","created":"2023-07-17","cited_by_count":108,"area":"lr"},{"id":"2402.04614","title":"Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Models","created":"2024-02-07","cited_by_count":105,"area":null},{"id":"2301.05062","title":"Tracr: Compiled Transformers as a Laboratory for Interpretability","created":"2023-01-12","cited_by_count":104,"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":"2104.14403","title":"Do Feature Attribution Methods Correctly Attribute Features?","created":"2021-04-27","cited_by_count":98,"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":"2212.09746","title":"Evaluating Human-Language Model Interaction","created":"2022-12-19","cited_by_count":92,"area":null},{"id":"2304.13007","title":"Answering Questions by Meta-Reasoning over Multiple Chains of Thought","created":"2023-04-25","cited_by_count":87,"area":"lr"},{"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":"2103.05154","title":"Explanations in Autonomous Driving: A Survey","created":"2021-03-09","cited_by_count":81,"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":"2302.13942","title":"Inseq: An Interpretability Toolkit for Sequence Generation Models","created":"2023-02-27","cited_by_count":78,"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":"2306.06427","title":"Boosting Language Models Reasoning with Chain-of-Knowledge Prompting","created":"2023-06-10","cited_by_count":77,"area":"lr"},{"id":"2310.04625","title":"Copy Suppression: Comprehensively Understanding an Attention Head","created":"2023-10-06","cited_by_count":76,"area":null},{"id":"2103.01378","title":"Contrastive Explanations for Model Interpretability","created":"2021-03-02","cited_by_count":75,"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":"2211.08073","title":"GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective","created":"2022-11-15","cited_by_count":72,"area":null},{"id":"2311.03731","title":"A Survey of Large Language Models Attribution","created":"2023-11-07","cited_by_count":71,"area":null},{"id":"2310.00280","title":"Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration","created":"2023-09-30","cited_by_count":70,"area":"lr"},{"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":"2307.16883","title":"HAGRID: A Human-LLM Collaborative Dataset for Generative Information-Seeking with Attribution","created":"2023-07-31","cited_by_count":56,"area":null},{"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":"2402.06044","title":"OpenToM: A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning Capabilities of Large Language Models","created":"2024-02-08","cited_by_count":54,"area":"lr"},{"id":"2108.11357","title":"ProoFVer: Natural Logic Theorem Proving for Fact Verification","created":"2021-08-25","cited_by_count":53,"area":null},{"id":"2202.05656","title":"Evaluation of post-hoc interpretability methods in time-series classification","created":"2022-02-11","cited_by_count":53,"area":null},{"id":"2408.08862","title":"Visual Agents as Fast and Slow Thinkers","created":"2024-08-16","cited_by_count":53,"area":"lr"},{"id":"2401.04536","title":"Evaluating Language Model Agency through Negotiations","created":"2024-01-09","cited_by_count":48,"area":null},{"id":"2502.14829","title":"Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps","created":"2025-02-20","cited_by_count":47,"area":"lr"},{"id":"2504.00125","title":"LLMs for Explainable AI: A Comprehensive Survey","created":"2025-03-31","cited_by_count":45,"area":null},{"id":"2504.14150","title":"Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations","created":"2025-04-19","cited_by_count":45,"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":"2310.00603","title":"Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals","created":"2023-10-01","cited_by_count":44,"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":"2301.12971","title":"Quantifying Context Mixing in Transformers","created":"2023-01-30","cited_by_count":43,"area":null},{"id":"2111.00358","title":"A Survey on the Robustness of Feature Importance and Counterfactual Explanations","created":"2021-10-30","cited_by_count":39,"area":null},{"id":"2204.05514","title":"A Comparative Study of Faithfulness Metrics for Model Interpretability Methods","created":"2022-04-12","cited_by_count":39,"area":"lr"},{"id":"2502.08554","title":"Fostering Appropriate Reliance on Large Language Models: The Role of Explanations, Sources, and Inconsistencies","created":"2025-02-12","cited_by_count":39,"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":"2104.05824","title":"Evaluating Saliency Methods for Neural Language Models","created":"2021-04-12","cited_by_count":37,"area":null},{"id":"2105.03287","title":"Order in the Court: Explainable AI Methods Prone to Disagreement","created":"2021-05-07","cited_by_count":36,"area":null},{"id":"2204.11790","title":"Can Rationalization Improve Robustness?","created":"2022-04-25","cited_by_count":36,"area":null},{"id":"2207.00056","title":"MultiViz: Towards Visualizing and Understanding Multimodal Models","created":"2022-06-30","cited_by_count":36,"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":"2112.06837","title":"Sparse Interventions in Language Models with Differentiable Masking","created":"2021-12-13","cited_by_count":34,"area":null},{"id":"2405.09308","title":"TimeX++: Learning Time-Series Explanations with Information Bottleneck","created":"2024-05-15","cited_by_count":33,"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":"2311.03533","title":"Quantifying Uncertainty in Natural Language Explanations of Large Language Models","created":"2023-11-06","cited_by_count":32,"area":null},{"id":"2103.11072","title":"Local Interpretations for Explainable Natural Language Processing: A Survey","created":"2021-03-20","cited_by_count":31,"area":null},{"id":"2106.01087","title":"Is Sparse Attention more Interpretable?","created":"2021-06-02","cited_by_count":31,"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":"2407.10747","title":"Codebook LLMs: Evaluating LLMs as Measurement Tools for Political Science Concepts","created":"2024-07-15","cited_by_count":30,"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":"2203.10261","title":"FaiRR: Faithful and Robust Deductive Reasoning over Natural Language","created":"2022-03-19","cited_by_count":29,"area":"lr"},{"id":"2209.14279","title":"Causal Proxy Models for Concept-Based Model Explanations","created":"2022-09-28","cited_by_count":29,"area":null},{"id":"2402.11863","title":"How Interpretable are Reasoning Explanations from Prompting Large Language Models?","created":"2024-02-19","cited_by_count":29,"area":"lr"},{"id":"2404.03189","title":"The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models","created":"2024-04-04","cited_by_count":29,"area":null},{"id":"2410.13032","title":"Hypothesis Testing the Circuit Hypothesis in LLMs","created":"2024-10-16","cited_by_count":29,"area":"mechinterp"},{"id":"2502.09083","title":"Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checking","created":"2025-02-13","cited_by_count":29,"area":null},{"id":"2109.06387","title":"Rationales for Sequential Predictions","created":"2021-09-14","cited_by_count":26,"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":"2401.13986","title":"Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning","created":"2024-01-25","cited_by_count":26,"area":null},{"id":"2501.17546","title":"Is Conversational XAI All You Need? Human-AI Decision Making With a Conversational XAI Assistant","created":"2025-01-29","cited_by_count":26,"area":null},{"id":"2510.04040","title":"FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning","created":"2025-10-05","cited_by_count":26,"area":"lr"},{"id":"2201.11569","title":"Human Interpretation of Saliency-based Explanation Over Text","created":"2022-01-27","cited_by_count":25,"area":null},{"id":"2202.01336","title":"Exploring Transformer Backbones for Heterogeneous Treatment Effect Estimation","created":"2022-02-02","cited_by_count":25,"area":null},{"id":"2204.03025","title":"Using Interactive Feedback to Improve the Accuracy and Explainability of Question Answering Systems Post-Deployment","created":"2022-04-06","cited_by_count":25,"area":null},{"id":"2211.13290","title":"SEAT: Stable and Explainable Attention","created":"2022-11-23","cited_by_count":25,"area":null},{"id":"2406.13663","title":"Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation","created":"2024-06-19","cited_by_count":25,"area":"rag"}],"next_cursor":"100"}