{"total":89,"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":"2305.15408","title":"Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective","created":"2023-05-24","cited_by_count":294,"area":"lr"},{"id":"2402.10200","title":"Chain-of-Thought Reasoning Without Prompting","created":"2024-02-15","cited_by_count":210,"area":"lr"},{"id":"2504.05419","title":"Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification","created":"2025-04-07","cited_by_count":159,"area":"lr"},{"id":"2502.06233","title":"Confidence Improves Self-Consistency in LLMs","created":"2025-02-10","cited_by_count":113,"area":"lr"},{"id":"2305.15054","title":"A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis","created":"2023-05-24","cited_by_count":89,"area":"lr"},{"id":"2506.02867","title":"Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning","created":"2025-06-03","cited_by_count":51,"area":"lr"},{"id":"2407.14507","title":"Internal Consistency and Self-Feedback in Large Language Models: A Survey","created":"2024-07-19","cited_by_count":50,"area":"lr"},{"id":"2406.03441","title":"Cycles of Thought: Measuring LLM Confidence through Stable Explanations","created":"2024-06-05","cited_by_count":29,"area":"lr"},{"id":"2502.06258","title":"Emergent Response Planning in LLMs","created":"2025-02-10","cited_by_count":19,"area":"lr"},{"id":"2605.09252","title":"LLM Agents Already Know When to Call Tools -- Even Without Reasoning","created":"2026-05-10","cited_by_count":19,"area":"lr"},{"id":"2507.12428","title":"Can We Predict Alignment Before Models Finish Thinking? Towards Monitoring Misaligned Reasoning Models","created":"2025-07-16","cited_by_count":17,"area":"lr"},{"id":"2602.09924","title":"LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations","created":"2026-02-10","cited_by_count":14,"area":"lr"},{"id":"2502.08922","title":"Self-Consistency of the Internal Reward Models Improves Self-Rewarding Language Models","created":"2025-02-13","cited_by_count":13,"area":"lr"},{"id":"2504.14379","title":"The Geometry of Self-Verification in a Task-Specific Reasoning Model","created":"2025-04-19","cited_by_count":13,"area":"lr"},{"id":"2505.17697","title":"Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models","created":"2025-05-23","cited_by_count":13,"area":"lr"},{"id":"2310.13439","title":"Self-Consistency of Large Language Models under Ambiguity","created":"2023-10-20","cited_by_count":12,"area":"lr"},{"id":"2410.03595","title":"Understanding Reasoning in Chain-of-Thought from the Hopfieldian View","created":"2024-10-04","cited_by_count":11,"area":"lr"},{"id":"2412.01113","title":"LLMs Faithfully and Iteratively Compute Answers During CoT: A Systematic Analysis With Multi-step Arithmetics","created":"2024-12-02","cited_by_count":11,"area":"lr"},{"id":"2601.08058","title":"Triggering Chain-of-Thought via Latent Feature Interventions in Large Language Models","created":"2026-01-12","cited_by_count":11,"area":"lr"},{"id":"2603.01326","title":"Truth as a Trajectory: What Internal Representations Reveal About Large Language Model Reasoning","created":"2026-03-01","cited_by_count":10,"area":"lr"},{"id":"2410.01556","title":"Integrative Decoding: Improve Factuality via Implicit Self-consistency","created":"2024-10-02","cited_by_count":8,"area":"lr"},{"id":"2601.22588","title":"Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry","created":"2026-01-30","cited_by_count":8,"area":"lr"},{"id":"2605.09502","title":"Hidden Error Awareness in Chain-of-Thought Reasoning: The Signal Is Diagnostic, Not Causal","created":"2026-05-10","cited_by_count":7,"area":"lr"},{"id":"2512.05325","title":"LYNX: Learning Dynamic Exits for Confidence-Controlled Reasoning","created":"2025-12-05","cited_by_count":6,"area":"lr"},{"id":"2601.03093","title":"ATLAS: Verifier-Guided Adaptive Latent Activation Steering for Efficient LLM Reasoning","created":"2026-01-06","cited_by_count":6,"area":"lr"},{"id":"2507.06087","title":"CoRE: Enhancing Metacognition with Label-free Self-evaluation in LRMs","created":"2025-07-08","cited_by_count":5,"area":"lr"},{"id":"2509.10004","title":"Unsupervised Hallucination Detection by Inspecting Reasoning Processes","created":"2025-09-12","cited_by_count":5,"area":"lr"},{"id":"2511.17910","title":"L2V-CoT: Cross-Modal Transfer of Chain-of-Thought Reasoning via Latent Intervention","created":"2025-11-22","cited_by_count":5,"area":"lr"},{"id":"2512.02914","title":"Martingale Score: An Unsupervised Metric for Bayesian Rationality in LLM Reasoning","created":"2025-12-02","cited_by_count":5,"area":"lr"},{"id":"2605.07579","title":"Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States","created":"2026-05-08","cited_by_count":5,"area":"lr"},{"id":"2605.17877","title":"PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization","created":"2026-05-18","cited_by_count":5,"area":"lr"},{"id":"2404.18988","title":"Markovian Transformers for Informative Language Modeling","created":"2024-04-29","cited_by_count":4,"area":"lr"},{"id":"2504.06650","title":"ThoughtProbe: Classifier-Guided Thought Space Exploration Leveraging LLM Intrinsic Reasoning","created":"2025-04-09","cited_by_count":4,"area":"lr"},{"id":"2601.00791","title":"Geometry of Reason: Spectral Signatures of Valid Mathematical Reasoning","created":"2026-01-02","cited_by_count":4,"area":"lr"},{"id":"2601.19847","title":"Identifying and Transferring Reasoning-Critical Neurons: Improving LLM Inference Reliability via Activation Steering","created":"2026-01-27","cited_by_count":4,"area":"lr"},{"id":"2605.07153","title":"Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs","created":"2026-05-08","cited_by_count":4,"area":"lr"},{"id":"2504.14175","title":"Hypothetical Documents or Knowledge Leakage? Rethinking LLM-based Query Expansion","created":"2025-04-19","cited_by_count":3,"area":"lr"},{"id":"2510.14665","title":"Beyond \"Hallucinations\": A Framework for Stable Human-AI Reasoning","created":"2025-10-16","cited_by_count":3,"area":"lr"},{"id":"2510.27355","title":"ThoughtProbe: Classifier-Guided LLM Thought Space Exploration via Probing Representations","created":"2025-10-31","cited_by_count":3,"area":"lr"},{"id":"2511.07483","title":"Beyond Correctness: Confidence-Aware Reward Modeling for Enhancing Large Language Model Reasoning","created":"2025-11-09","cited_by_count":3,"area":"lr"},{"id":"2601.21183","title":"Sycophantic Anchors: Localizing and Quantifying User Agreement in Reasoning Models","created":"2026-01-29","cited_by_count":3,"area":"lr"},{"id":"2606.10646","title":"How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs","created":"2026-06-09","cited_by_count":3,"area":"lr"},{"id":"2601.03052","title":"Detecting Hallucinations in Retrieval-Augmented Generation via Semantic-level Internal Reasoning Graph","created":"2026-01-06","cited_by_count":2,"area":"lr"},{"id":"2601.17593","title":"From Chains to DAGs: Probing the Graph Structure of Reasoning in LLMs","created":"2026-01-24","cited_by_count":2,"area":"lr"},{"id":"2602.17691","title":"Tethered Reasoning: Decoupling Entropy from Hallucination in Quantized LLMs via Manifold Steering","created":"2026-02-06","cited_by_count":2,"area":"lr"},{"id":"2604.23460","title":"Ulterior Motives: Detecting Misaligned Reasoning in Continuous Thought Models","created":"2026-04-25","cited_by_count":2,"area":"lr"},{"id":"2605.06723","title":"When Does a Language Model Commit? A Finite-Answer Theory of Pre-Verbalization Commitment","created":"2026-05-07","cited_by_count":2,"area":"lr"},{"id":"2605.11467","title":"Drop the Act: Probe-Filtered RL for Faithful Chain-of-Thought Reasoning","created":"2026-05-12","cited_by_count":2,"area":"lr"},{"id":"2605.11746","title":"When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight Channel","created":"2026-05-12","cited_by_count":2,"area":"lr"},{"id":"2605.13772","title":"Where Does Reasoning Break? Step-Level Hallucination Detection via Hidden-State Transport Geometry","created":"2026-05-13","cited_by_count":2,"area":"lr"},{"id":"2605.28301","title":"Better Accuracies, Worse Reasoning: A Step-Level Audit of Medical Chain-of-Thought Distillation","created":"2026-05-27","cited_by_count":2,"area":"lr"},{"id":"2605.28823","title":"What are They Thinking? Delineation, Probing, and Tracking of Concepts in LLMs","created":"2026-04-07","cited_by_count":2,"area":"lr"},{"id":"2410.13216","title":"Anchored Alignment for Self-Explanations Enhancement","created":"2024-10-17","cited_by_count":1,"area":"lr"},{"id":"2507.10007","title":"Deep Hidden Cognition Facilitates Reliable Chain-of-Thought Reasoning","created":"2025-07-14","cited_by_count":1,"area":"lr"},{"id":"2508.04576","title":"ConfProBench: A Confidence Evaluation Benchmark for MLLM-Based Process Judges","created":"2025-08-06","cited_by_count":1,"area":"lr"},{"id":"2509.10753","title":"HalluField: Detecting LLM Hallucinations via Field-Theoretic Modeling","created":"2025-09-12","cited_by_count":1,"area":"lr"},{"id":"2602.20338","title":"Emergent Manifold Separability during Reasoning in Large Language Models","created":"2026-02-23","cited_by_count":1,"area":"lr"},{"id":"2603.01025","title":"One-Token Verification for Reasoning Correctness Estimation","created":"2026-03-01","cited_by_count":1,"area":"lr"},{"id":"2603.21006","title":"How AI Systems Think About Education: Analyzing Latent Preference Patterns in Large Language Models","created":"2026-02-28","cited_by_count":1,"area":"lr"},{"id":"2604.02113","title":"Reliable Control-Point Selection for Steering Reasoning in Large Language Models","created":"2026-04-02","cited_by_count":1,"area":"lr"},{"id":"2604.13759","title":"The cognitive companion: a lightweight parallel monitoring architecture for detecting and recovering from reasoning degradation in LLM agents","created":"2026-04-15","cited_by_count":1,"area":"lr"},{"id":"2604.16217","title":"Beyond Surface Statistics: Robust Conformal Prediction for LLMs via Internal Representations","created":"2026-04-17","cited_by_count":1,"area":"lr"},{"id":"2605.21770","title":"Manifold-Guided Attention Steering","created":"2026-05-20","cited_by_count":1,"area":"lr"},{"id":"2605.27712","title":"Prefix-Safe Bayesian Belief Tracking for LLM Reasoning Reliability:Separating Calibration from Ranking","created":"2026-05-26","cited_by_count":1,"area":"lr"},{"id":"2609.02438","title":"When Decodability Is Not Enough: Logical Validity Representations, Behavioral Dissociation, and Causal Tests in Language Models","created":"2026-09-02","cited_by_count":1,"area":"lr"},{"id":"2610.16371","title":"Rule vs.Consequence: Dissociable Internal Representations of Moral Reasoning in LLMs","created":"2026-10-12","cited_by_count":1,"area":"lr"},{"id":"2509.00371","title":"Two Causes, Not One: Rethinking Omission and Fabrication Hallucinations in MLLMs","created":"2025-08-30","cited_by_count":0,"area":"lr"},{"id":"2511.04053","title":"Interpreting Multi-Attribute Confounding through Numerical Attributes in Large Language Models","created":"2025-11-06","cited_by_count":0,"area":"lr"},{"id":"2511.12155","title":"Rethinking Deep Alignment Through The Lens Of Incomplete Learning","created":"2025-11-15","cited_by_count":0,"area":"lr"},{"id":"2601.01011","title":"Intention Collapse: Intention-Level Metrics for Reasoning in Language Models","created":"2026-01-03","cited_by_count":0,"area":"lr"},{"id":"2601.13358","title":"The Geometry of Thought: How Scale Restructures Reasoning In Large Language Models","created":"2026-01-19","cited_by_count":0,"area":"lr"},{"id":"2601.17467","title":"Harnessing Reasoning Trajectories for Hallucination Detection via Answer-agreement Representation Shaping","created":"2026-01-24","cited_by_count":0,"area":"lr"},{"id":"2601.22484","title":"Mitigating Cognitive Inertia in Large Reasoning Models via Latent Spike Steering","created":"2026-01-30","cited_by_count":0,"area":"lr"},{"id":"2602.20332","title":"No One Size Fits All: QueryBandits for Hallucination Mitigation","created":"2026-02-23","cited_by_count":0,"area":"lr"},{"id":"2606.15982","title":"Mind the Gap: Diagnosing Constraint Discovery Failures in Text-in-Image Editing","created":"2026-06-14","cited_by_count":0,"area":"lr"},{"id":"2608.01014","title":"Cloud-ScPO: Hidden-State Geometry for Semi-Supervised Preference Optimization in LLM Reasoning","created":"2026-08-02","cited_by_count":0,"area":"lr"},{"id":"2608.05660","title":"Reasoning Errors Have a Region and a Direction in the Residual-Stream Trajectory of LLMs","created":"2026-08-06","cited_by_count":0,"area":"lr"},{"id":"2608.18581","title":"From Storage to Access: Verifiable Activation of Parametric Knowledge in LLMs via Explicit Priming and Implicit Reasoning","created":"2026-08-19","cited_by_count":0,"area":"lr"},{"id":"2608.18628","title":"When Safety Overrides Vision: Exploring Dynamics between Vision Influence and Safety Alignment in Vision-Language Models","created":"2026-08-19","cited_by_count":0,"area":"lr"},{"id":"2608.29070","title":"Selective Disclosure of Hidden Directives in Reasoning Models: Behavioral Asymmetry and Steering","created":"2026-08-29","cited_by_count":0,"area":"lr"},{"id":"2608.29431","title":"Evaluating the Semantic Specificity of Representation Steering in Language Models","created":"2026-08-29","cited_by_count":0,"area":"lr"},{"id":"2608.30841","title":"HSRM: Hidden-State Reward Models for Test-Time Verification","created":"2026-08-31","cited_by_count":0,"area":"lr"},{"id":"2608.31068","title":"Wrong Prediction, Right Answer: Recovering Evidence from Collapsed LLM Sequence Scores","created":"2026-08-31","cited_by_count":0,"area":"lr"},{"id":"2609.27041","title":"Math Reasoning in LLMs is Organized by Approach, Not Topic","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2609.29875","title":"When Can Agents Forget Their Reasoning? ICLR for Long-Horizon Agent Context Compression","created":"2026-09-24","cited_by_count":0,"area":"lr"},{"id":"2609.33290","title":"Calibration, Not Answer Selection: Distilling Internal Confidence in Reasoning Models","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.36371","title":"LatentSift: Policy-State Filtering for Token-Efficient Verification of Software Engineering Agents","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.05976","title":"Can Language Models Learn to Reject Their Own Bad Reasoning Steps?","created":"2026-10-05","cited_by_count":0,"area":"lr"}],"next_cursor":null}