{"total":40,"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":"2505.05410","title":"Reasoning Models Don't Always Say What They Think","created":"2025-05-08","cited_by_count":415,"area":"lr"},{"id":"2307.11768","title":"Question Decomposition Improves the Faithfulness of Model-Generated Reasoning","created":"2023-07-17","cited_by_count":108,"area":"lr"},{"id":"2211.01562","title":"PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales","created":"2022-11-03","cited_by_count":56,"area":"lr"},{"id":"2306.03100","title":"Rethinking Model Evaluation as Narrowing the Socio-Technical Gap","created":"2023-06-01","cited_by_count":56,"area":"lr"},{"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":"2403.05518","title":"Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought","created":"2024-03-08","cited_by_count":39,"area":"lr"},{"id":"2502.17026","title":"Understanding the Uncertainty of LLM Explanations: A Perspective Based on Reasoning Topology","created":"2025-02-24","cited_by_count":25,"area":"lr"},{"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":"2602.20710","title":"Counterfactual Simulation Training for Chain-of-Thought Faithfulness","created":"2026-02-24","cited_by_count":17,"area":"lr"},{"id":"2401.00139","title":"Enhancing Causal Reasoning in Large Language Models: A Causal Attribution Model for Precision Fine-Tuning","created":"2023-12-30","cited_by_count":14,"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":"2508.16695","title":"Do Cognitively Interpretable Reasoning Traces Improve LLM Performance?","created":"2025-08-21","cited_by_count":11,"area":"lr"},{"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":"2310.05797","title":"In-Context Explainers: Harnessing LLMs for Explaining Black Box Models","created":"2023-10-09","cited_by_count":9,"area":"lr"},{"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":"2410.05168","title":"ReasoningRank: Teaching Student Models to Rank through Reasoning-Based Knowledge Distillation","created":"2024-10-07","cited_by_count":9,"area":"lr"},{"id":"2505.13792","title":"Interpretable Traces, Unexpected Outcomes: Investigating the Disconnect in Trace-Based Knowledge Distillation","created":"2025-05-20","cited_by_count":8,"area":"lr"},{"id":"2504.04699","title":"R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation","created":"2025-04-07","cited_by_count":7,"area":"lr"},{"id":"2203.05843","title":"An Interpretable Neuro-Symbolic Reasoning Framework for Task-Oriented Dialogue Generation","created":"2022-03-11","cited_by_count":5,"area":"lr"},{"id":"2303.06223","title":"Who's Thinking? A Push for Human-Centered Evaluation of LLMs using the XAI Playbook","created":"2023-03-10","cited_by_count":5,"area":"lr"},{"id":"2601.11517","title":"Do explanations generalize across large reasoning models?","created":"2026-01-16","cited_by_count":5,"area":"lr"},{"id":"2601.21210","title":"Uncovering Hidden Correctness in LLM Causal Reasoning via Symbolic Verification","created":"2026-01-29","cited_by_count":5,"area":"lr"},{"id":"2510.14741","title":"DEXTER: Diffusion-Guided EXplanations with TExtual Reasoning for Vision Models","created":"2025-10-16","cited_by_count":4,"area":"lr"},{"id":"2511.11187","title":"ReTrace: Interactive Visualizations for Reasoning Traces of Large Reasoning Models","created":"2025-11-14","cited_by_count":3,"area":"lr"},{"id":"2512.00163","title":"Measuring What LLMs Think They Do: SHAP Faithfulness and Deployability on Financial Tabular Classification","created":"2025-11-28","cited_by_count":3,"area":"lr"},{"id":"2503.10652","title":"Can Large Language Models Simulate Human Responses? A Case Study of Stated Preference Experiments in the Context of Heating-related Choices","created":"2025-03-07","cited_by_count":2,"area":"lr"},{"id":"2507.16395","title":"LLM-Driven Collaborative Model for Untangling Commits via Explicit and Implicit Dependency Reasoning","created":"2025-07-22","cited_by_count":2,"area":"lr"},{"id":"2509.21559","title":"X-CoT: Explainable Text-to-Video Retrieval via LLM-based Chain-of-Thought Reasoning","created":"2025-09-25","cited_by_count":2,"area":"lr"},{"id":"2605.09906","title":"Separate First, Fuse Later: Mitigating Cross-Modal Interference in Audio-Visual LLMs Reasoning with Modality-Specific Chain-of-Thought","created":"2026-05-11","cited_by_count":2,"area":"lr"},{"id":"2308.02950","title":"A criterion for Artificial General Intelligence: hypothetic-deductive reasoning, tested on ChatGPT","created":"2023-08-05","cited_by_count":1,"area":"lr"},{"id":"2502.10732","title":"Rule-Bottleneck Reinforcement Learning: Joint Explanation and Decision Optimization for Resource Allocation with Language Agents","created":"2025-02-15","cited_by_count":1,"area":"lr"},{"id":"2506.10853","title":"A Study on Individual Spatiotemporal Activity Generation Method Using MCP-Enhanced Chain-of-Thought Large Language Models","created":"2025-06-12","cited_by_count":1,"area":"lr"},{"id":"2508.04939","title":"I Think, Therefore I Am Under-Qualified? A Benchmark for Evaluating Linguistic Shibboleth Detection in LLM Hiring Evaluations","created":"2025-08-06","cited_by_count":1,"area":"lr"},{"id":"2603.13256","title":"Training-Free Agentic AI: Probabilistic Control and Coordination in Multi-Agent LLM Systems","created":"2026-02-24","cited_by_count":1,"area":"lr"},{"id":"2503.03693","title":"ILLC: Iterative Layer-by-Layer Compression for Enhancing Structural Faithfulness in SpArX","created":"2025-03-05","cited_by_count":0,"area":"lr"},{"id":"2506.21580","title":"From General Reasoning to Domain Expertise: Uncovering the Limits of Generalization in Large Language Models","created":"2025-06-16","cited_by_count":0,"area":"lr"},{"id":"2509.07017","title":"From Eigenmodes to Proofs: Integrating Graph Spectral Operators with Symbolic Interpretable Reasoning","created":"2025-09-07","cited_by_count":0,"area":"lr"},{"id":"2605.02962","title":"ISAAC: Auditing Causal Reasoning in Deep Models for Drug-Target Interaction","created":"2026-05-03","cited_by_count":0,"area":"lr"},{"id":"2609.06976","title":"HealthLoopQA: A Context-Aware Question Answering Benchmark for Interpreting Wearable Monitoring Data in Diabetes Care","created":"2026-09-07","cited_by_count":0,"area":"lr"}],"next_cursor":null}