{"total":107,"rows":[{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"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":"2402.01761","title":"Rethinking Interpretability in the Era of Large Language Models","created":"2024-01-30","cited_by_count":111,"area":"lr"},{"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":"2401.07927","title":"Are self-explanations from Large Language Models faithful?","created":"2024-01-15","cited_by_count":101,"area":null},{"id":"2410.03727","title":"FaithEval: Can Your Language Model Stay Faithful to Context, Even If \"The Moon is Made of Marshmallows\"","created":"2024-09-30","cited_by_count":86,"area":"rag"},{"id":"2402.17700","title":"RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations","created":"2024-02-27","cited_by_count":79,"area":"mechinterp"},{"id":"2501.08156","title":"Are DeepSeek R1 And Other Reasoning Models More Faithful?","created":"2025-01-14","cited_by_count":72,"area":"lr"},{"id":"2506.13206","title":"Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models","created":"2025-06-16","cited_by_count":65,"area":"lr"},{"id":"2504.13151","title":"MIB: A Mechanistic Interpretability Benchmark","created":"2025-04-17","cited_by_count":56,"area":"mechinterp"},{"id":"2502.14829","title":"Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps","created":"2025-02-20","cited_by_count":47,"area":"lr"},{"id":"2309.10312","title":"Rigorously Assessing Natural Language Explanations of Neurons","created":"2023-09-19","cited_by_count":45,"area":null},{"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":"2405.01379","title":"Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving","created":"2024-05-02","cited_by_count":35,"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":"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":"2311.01270","title":"People Make Better Edits: Measuring the Efficacy of LLM-Generated Counterfactually Augmented Data for Harmful Language Detection","created":"2023-11-02","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"},{"id":"2505.17120","title":"Self-Interpretability: LLMs Can Describe Complex Internal Processes that Drive Their Decisions","created":"2025-05-21","cited_by_count":25,"area":null},{"id":"2404.18624","title":"Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?","created":"2024-04-29","cited_by_count":24,"area":null},{"id":"2402.08699","title":"Unsupervised Evaluation of Code LLMs with Round-Trip Correctness","created":"2024-02-13","cited_by_count":23,"area":null},{"id":"2505.13774","title":"Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models","created":"2025-05-19","cited_by_count":23,"area":"lr"},{"id":"2411.05764","title":"FinDVer: Explainable Claim Verification over Long and Hybrid-Content Financial Documents","created":"2024-11-08","cited_by_count":19,"area":null},{"id":"2507.22928","title":"How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding","created":"2025-07-24","cited_by_count":19,"area":"lr"},{"id":"2406.19482","title":"xTower: A Multilingual LLM for Explaining and Correcting Translation Errors","created":"2024-06-27","cited_by_count":17,"area":null},{"id":"2510.27378","title":"Measuring Chain-of-Thought Monitorability Through Faithfulness and Verbosity","created":"2025-10-31","cited_by_count":17,"area":"lr"},{"id":"2602.20710","title":"Counterfactual Simulation Training for Chain-of-Thought Faithfulness","created":"2026-02-24","cited_by_count":17,"area":"lr"},{"id":"2509.00190","title":"Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics","created":"2025-08-29","cited_by_count":16,"area":"lr"},{"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":"2504.15205","title":"Support Evaluation for the TREC 2024 RAG Track: Comparing Human versus LLM Judges","created":"2025-04-21","cited_by_count":14,"area":"rag"},{"id":"2410.16676","title":"CausalEval: Towards Better Causal Reasoning in Language Models","created":"2024-10-22","cited_by_count":13,"area":"lr"},{"id":"2602.02639","title":"A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior","created":"2026-02-02","cited_by_count":13,"area":"lr"},{"id":"2502.18848","title":"A Causal Lens for Evaluating Faithfulness Metrics","created":"2025-02-26","cited_by_count":12,"area":null},{"id":"2505.23945","title":"A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models","created":"2025-05-29","cited_by_count":12,"area":"lr"},{"id":"2403.14459","title":"Multi-Level Explanations for Generative Language Models","created":"2024-03-21","cited_by_count":11,"area":null},{"id":"2505.22823","title":"Self-Critique and Refinement for Faithful Natural Language Explanations","created":"2025-05-28","cited_by_count":10,"area":null},{"id":"2509.13316","title":"Do Activation Verbalization Methods Convey Privileged Information?","created":"2025-09-16","cited_by_count":10,"area":"mechinterp"},{"id":"2409.07123","title":"Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandem","created":"2024-09-11","cited_by_count":9,"area":"lr"},{"id":"2504.05294","title":"Truthful or Fabricated? Using Causal Attribution to Mitigate Reward Hacking in Explanations","created":"2025-04-07","cited_by_count":9,"area":"lr"},{"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":"2402.12038","title":"Self-AMPLIFY: Improving Small Language Models with Self Post Hoc Explanations","created":"2024-02-19","cited_by_count":8,"area":null},{"id":"2602.10117","title":"Biases in the Blind Spot: Detecting What LLMs Fail to Mention","created":"2026-02-10","cited_by_count":8,"area":"lr"},{"id":"2403.20322","title":"Towards a Framework for Evaluating Explanations in Automated Fact Verification","created":"2024-03-29","cited_by_count":7,"area":null},{"id":"2407.20899","title":"Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline Approach","created":"2024-07-30","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":"2508.07117","title":"From Nodes to Narratives: Explaining Graph Neural Networks with LLMs and Graph Context","created":"2025-08-09","cited_by_count":6,"area":null},{"id":"2510.13272","title":"Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation","created":"2025-10-15","cited_by_count":6,"area":"lr"},{"id":"2402.10767","title":"Inference to the Best Explanation in Large Language Models","created":"2024-02-16","cited_by_count":5,"area":null},{"id":"2410.12284","title":"Fool Me Once? Contrasting Textual and Visual Explanations in a Clinical Decision-Support Setting","created":"2024-10-16","cited_by_count":5,"area":null},{"id":"2510.24236","title":"Towards Transparent Reasoning: What Drives Faithfulness in Large Language Models?","created":"2025-10-28","cited_by_count":5,"area":"lr"},{"id":"2601.00282","title":"Can Large Language Models Still Explain Themselves? Investigating the Impact of Quantization on Self-Explanations","created":"2026-01-01","cited_by_count":5,"area":null},{"id":"2306.02980","title":"KNOW How to Make Up Your Mind! Adversarially Detecting and Alleviating Inconsistencies in Natural Language Explanations","created":"2023-06-05","cited_by_count":4,"area":null},{"id":"2310.05442","title":"Establishing Trustworthiness: Rethinking Tasks and Model Evaluation","created":"2023-10-09","cited_by_count":4,"area":"lr"},{"id":"2407.01384","title":"Free-text Rationale Generation under Readability Level Control","created":"2024-07-01","cited_by_count":4,"area":null},{"id":"2506.07523","title":"Aligning What LLMs Do and Say: Towards Self-Consistent Explanations","created":"2025-06-09","cited_by_count":4,"area":"alignment"},{"id":"2403.19424","title":"The Role of Syntactic Span Preferences in Post-Hoc Explanation Disagreement","created":"2024-03-28","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":"2411.02664","title":"Explanations that reveal all through the definition of encoding","created":"2024-11-04","cited_by_count":3,"area":null},{"id":"2412.12318","title":"Graph-Guided Textual Explanation Generation Framework","created":"2024-12-16","cited_by_count":3,"area":null},{"id":"2509.11026","title":"Rethinking Human Preference Evaluation of LLM Rationales","created":"2025-09-14","cited_by_count":3,"area":"lr"},{"id":"2603.14643","title":"Argumentation for Explainable and Globally Contestable Decision Support with LLMs","created":"2026-03-15","cited_by_count":3,"area":null},{"id":"2605.25052","title":"Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth","created":"2026-05-24","cited_by_count":3,"area":null},{"id":"2311.07556","title":"Using Natural Language Explanations to Improve Robustness of In-context Learning","created":"2023-11-13","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":"2506.19113","title":"Argument-Based Consistency in Toxicity Explanations of LLMs","created":"2025-06-23","cited_by_count":2,"area":null},{"id":"2508.00171","title":"On the Risk of Misleading Reports: Diagnosing Textual Biases in Multimodal Clinical AI","created":"2025-07-31","cited_by_count":2,"area":null},{"id":"2607.14123","title":"Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methods","created":"2026-06-18","cited_by_count":2,"area":"mechinterp"},{"id":"2310.13506","title":"Explaining Interactions Between Text Spans","created":"2023-10-20","cited_by_count":1,"area":null},{"id":"2505.17855","title":"Explaining Sources of Uncertainty in Automated Fact-Checking","created":"2025-05-23","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":"2511.01706","title":"Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement","created":"2025-11-03","cited_by_count":1,"area":null},{"id":"2511.20233","title":"REFLEX: Self-Refining Explainable Fact-Checking via Verdict-Anchored Style Control","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2512.06814","title":"CAuSE: Decoding Multimodal Classifiers using Faithful Natural Language Explanation","created":"2025-12-07","cited_by_count":1,"area":null},{"id":"2601.10649","title":"MINERVA-Cultural: A Benchmark for Cultural and Multilingual Long Video Reasoning","created":"2026-01-15","cited_by_count":1,"area":"lr"},{"id":"2604.12069","title":"Robust Explanations for User Trust in Enterprise NLP Systems","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2604.13392","title":"ReSS: Learning Reasoning Models for Tabular Data Prediction via Symbolic Scaffold","created":"2026-04-15","cited_by_count":1,"area":"lr"},{"id":"2606.01148","title":"Not All Explanations Simulate Equally: Comparing Verbalized Feature Attributions and Self-Generated Rationales","created":"2026-05-31","cited_by_count":1,"area":"synth"},{"id":"2607.06648","title":"Final Checkpoints Are Not Enough: Analyzing Latent Reasoning Faithfulness Along Training Trajectories","created":"2026-07-07","cited_by_count":1,"area":null},{"id":"2402.04787","title":"A Hypothesis-Driven Framework for the Analysis of Self-Rationalising Models","created":"2024-02-07","cited_by_count":0,"area":null},{"id":"2503.05737","title":"Local Differences, Global Lessons: Insights from Organisation Policies for International Legislation","created":"2025-02-19","cited_by_count":0,"area":null},{"id":"2503.08815","title":"Cross-Examiner: Evaluating Consistency of Large Language Model-Generated Explanations","created":"2025-03-11","cited_by_count":0,"area":null},{"id":"2506.09277","title":"NeuroFaith: Evaluating LLM Self-Explanation Faithfulness via Internal Representation Alignment","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2510.18810","title":"When LRP Diverges from Leave-One-Out in Transformers","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2512.07288","title":"Investigating Training and Generalization in Faithful Self-Explanations of Large Language Models","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2601.13122","title":"Responsible AI for General-Purpose Systems: Overview, Challenges, and A Path Forward","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2603.18752","title":"WeNLEX: Weakly Supervised Natural Language Explanations for Multilabel Chest X-ray Classification","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2604.14325","title":"Faithfulness Serum: Mitigating the Faithfulness Gap in Textual Explanations of LLM Decisions via Attribution Guidance","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2606.15325","title":"Prior over Evidence: Stereotype-Driven Diagnosis in LLM-Based L2 Pronunciation Feedback","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2606.15779","title":"Faithful Action-unit Causal Reasoning for Counterfactually Faithful Emotion Explanations","created":"2026-06-14","cited_by_count":0,"area":"lr"},{"id":"2606.28615","title":"What LLMs explain is not what they believe: Evaluating explanation sufficiency under models' own input beliefs","created":"2026-06-26","cited_by_count":0,"area":"lr"},{"id":"2607.06327","title":"Estimating Uncertainty from Reasoning: A Large-Scale Study of Multi- and Crosslingual MCQA Performance in LLMs","created":"2026-07-07","cited_by_count":0,"area":"lr"},{"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":"2607.21090","title":"Training Large Language Models for Self-Explanation Faithfulness","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.15685","title":"Counterfactual Sensitivity Is Not Repairability: Auditing Replay Probes for Video Evidence","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.21043","title":"Evidence-Consistent Generative Detection under Scenario-Level Distribution Shift","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.07596","title":"I Don't Miss You, but I Do: Self-Explanation Faithfulness of Modality Missingness in Vision-Language Models","created":"2026-09-07","cited_by_count":0,"area":"mllm"},{"id":"2609.08585","title":"Limitations of Automated Simulatability: LLM Simulators Can Bypass Explanations","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.17119","title":"An Empirical Study of Counterfactual Self-Explanations in LLMs","created":"2026-09-15","cited_by_count":0,"area":null}],"next_cursor":"100"}