{"total":73,"rows":[{"id":"2412.14171","title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","created":"2024-12-18","cited_by_count":611,"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":"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":"2502.14829","title":"Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps","created":"2025-02-20","cited_by_count":47,"area":"lr"},{"id":"2411.05345","title":"Reasoning Robustness of LLMs to Adversarial Typographical Errors","created":"2024-11-08","cited_by_count":31,"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":"2402.14897","title":"Chain-of-Thought Unfaithfulness as Disguised Accuracy","created":"2024-02-22","cited_by_count":28,"area":"lr"},{"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":"2405.15092","title":"Dissociation of Faithful and Unfaithful Reasoning in LLMs","created":"2024-05-23","cited_by_count":23,"area":"lr"},{"id":"2405.18915","title":"Towards Better Chain-of-Thought: A Reflection on Effectiveness and Faithfulness","created":"2024-05-29","cited_by_count":20,"area":"lr"},{"id":"2509.09396","title":"LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations","created":"2025-09-11","cited_by_count":16,"area":"synth"},{"id":"2505.00268","title":"Consistency in Language Models: Current Landscape, Challenges, and Future Directions","created":"2025-05-01","cited_by_count":14,"area":null},{"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":"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":"2505.22823","title":"Self-Critique and Refinement for Faithful Natural Language Explanations","created":"2025-05-28","cited_by_count":10,"area":null},{"id":"2406.16144","title":"Chain-of-Probe: Examining the Necessity and Accuracy of CoT Step-by-Step","created":"2024-06-23","cited_by_count":8,"area":"lr"},{"id":"2410.15268","title":"GraphNarrator: Generating Textual Explanations for Graph Neural Networks","created":"2024-10-20","cited_by_count":7,"area":null},{"id":"2511.08409","title":"Faithful-First Reasoning, Planning, and Acting for Multimodal LLMs","created":"2025-11-11","cited_by_count":7,"area":"lr"},{"id":"2502.12530","title":"Translate Policy to Language: Flow Matching Generated Rewards for LLM Explanations","created":"2025-02-18","cited_by_count":6,"area":"alignment"},{"id":"2507.13328","title":"Vision-and-Language Training Helps Deploy Taxonomic Knowledge but Does Not Fundamentally Alter It","created":"2025-07-17","cited_by_count":6,"area":null},{"id":"2509.23676","title":"From Reasoning to Answer: Empirical, Attention-Based and Mechanistic Insights into Distilled DeepSeek R1 Models","created":"2025-09-28","cited_by_count":6,"area":"lr"},{"id":"2510.13272","title":"Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation","created":"2025-10-15","cited_by_count":6,"area":"lr"},{"id":"2603.16475","title":"Breaking the Chain: A Causal Analysis of LLM Faithfulness to Intermediate Structures","created":"2026-03-17","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":"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":"2506.07523","title":"Aligning What LLMs Do and Say: Towards Self-Consistent Explanations","created":"2025-06-09","cited_by_count":4,"area":"alignment"},{"id":"2601.06973","title":"LLMs Can't Play Hangman: On the Necessity of a Private Working Memory for Language Agents","created":"2026-01-11","cited_by_count":4,"area":"agents"},{"id":"2603.20172","title":"Measuring Faithfulness Depends on How You Measure: Classifier Sensitivity in LLM Chain-of-Thought Evaluation","created":"2026-03-20","cited_by_count":4,"area":"lr"},{"id":"2409.15359","title":"Watch Your Steps: Observable and Modular Chains of Thought","created":"2024-09-17","cited_by_count":3,"area":"lr"},{"id":"2412.12318","title":"Graph-Guided Textual Explanation Generation Framework","created":"2024-12-16","cited_by_count":3,"area":null},{"id":"2509.15403","title":"Quantifying Uncertainty in Natural Language Explanations of Large Language Models for Question Answering","created":"2025-09-18","cited_by_count":3,"area":null},{"id":"2510.01048","title":"Interpreting Language Models Through Concept Descriptions: A Survey","created":"2025-10-01","cited_by_count":3,"area":"mechinterp"},{"id":"2512.02340","title":"Reasoning Path and Latent State Analysis for Multi-view Visual Spatial Reasoning: A Cognitive Science Perspective","created":"2025-12-02","cited_by_count":3,"area":"lr"},{"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":"2403.13369","title":"Clinical information extraction for Low-resource languages with Few-shot learning using Pre-trained language models and Prompting","created":"2024-03-20","cited_by_count":2,"area":null},{"id":"2505.24217","title":"Semi-structured LLM Reasoners Can Be Rigorously Audited","created":"2025-05-30","cited_by_count":2,"area":"lr"},{"id":"2506.15925","title":"Reranking-based Generation for Unbiased Perspective Summarization","created":"2025-06-19","cited_by_count":2,"area":null},{"id":"2509.20641","title":"Investigating Modality Contribution in Audio LLMs for Music","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2510.04392","title":"Improving Consistency in Retrieval-Augmented Systems with Group Similarity Rewards","created":"2025-10-05","cited_by_count":2,"area":"rag"},{"id":"2510.17256","title":"Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations","created":"2025-10-20","cited_by_count":2,"area":"mechinterp"},{"id":"2510.22362","title":"Mapping Faithful Reasoning in Language Models","created":"2025-10-25","cited_by_count":2,"area":"lr"},{"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":"2410.03296","title":"A Systematic Comparison between Extractive Self-Explanations and Human Rationales in Text Classification","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2410.13216","title":"Anchored Alignment for Self-Explanations Enhancement","created":"2024-10-17","cited_by_count":1,"area":"lr"},{"id":"2506.13746","title":"Evaluating Large Language Models for Phishing Detection, Self-Consistency, Faithfulness, and Explainability","created":"2025-06-16","cited_by_count":1,"area":"lr"},{"id":"2509.16666","title":"Robust Native Language Identification through Agentic Decomposition","created":"2025-09-20","cited_by_count":1,"area":"agents"},{"id":"2510.21884","title":"Support-Contra Asymmetry in LLM Explanations","created":"2025-10-23","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":"2505.11772","title":"LAMP: Extracting Local Decision Surfaces From Large Language Models","created":"2025-05-17","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":"2508.09776","title":"Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study","created":"2025-08-13","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":"2602.14529","title":"Disentangling Deception and Hallucination Failures in LLMs","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2602.18262","title":"Simplifying Outcomes of Language Model Component Analyses with ELIA","created":"2026-02-20","cited_by_count":0,"area":"mechinterp"},{"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":"2604.14325","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":"2604.23701","title":"Agri-CPJ: A Training-Free Explainable Framework for Agricultural Pest Diagnosis Using Caption-Prompt-Judge and LLM-as-a-Judge","created":"2026-04-26","cited_by_count":0,"area":null},{"id":"2606.19750","title":"Manifold Bandits: Bayesian Curriculum Learning over the Latent Geometry of Large Language Models","created":"2026-06-18","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":"2607.15957","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":"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":"2609.22553","title":"Correct Diagnosis, Better Feedback: A Symbolic-Verifier for Faithful LLM Tutoring Feedback in Logic Proofs","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.24677","title":"TimeLitmus: A Diagnostic Benchmark for Cross-Modal Understanding and Explanation Faithfulness in Event-Conditioned Time-Series Prediction","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.29496","title":"Evaluating Explanation-Driven Vision-Language Reasoning via Generation Order Interventions","created":"2026-08-26","cited_by_count":0,"area":"lr"},{"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":"2610.00018","title":"What Do Rationales Communicate? A Message-Intervention Study in Role-Specialized QA","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2610.00314","title":"Predictive Credit: Measuring What Scientific Explanations Add to Experimental Forecasts","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2610.03509","title":"Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability","created":"2026-10-02","cited_by_count":0,"area":"lr"}],"next_cursor":null}