{"total":59,"rows":[{"id":"2401.06751","title":"The Unreasonable Effectiveness of Easy Training Data for Hard Tasks","created":"2024-01-12","cited_by_count":40,"area":"lr"},{"id":"2503.03730","title":"Towards Understanding Distilled Reasoning Models: A Representational Approach","created":"2025-03-05","cited_by_count":26,"area":"lr"},{"id":"2402.10688","title":"Towards Uncovering How Large Language Model Works: An Explainability Perspective","created":"2024-02-16","cited_by_count":22,"area":"lr"},{"id":"2503.23084","title":"The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction","created":"2025-03-29","cited_by_count":21,"area":"lr"},{"id":"2510.09782","title":"The Geometry of Reasoning: Flowing Logics in Representation Space","created":"2025-10-10","cited_by_count":21,"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":"2510.24941","title":"Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thought","created":"2025-10-28","cited_by_count":15,"area":"lr"},{"id":"2504.17130","title":"Steering the CensorShip: Uncovering Representation Vectors for LLM \"Thought\" Control","created":"2025-04-23","cited_by_count":14,"area":"lr"},{"id":"2505.15634","title":"Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models","created":"2025-05-21","cited_by_count":13,"area":"lr"},{"id":"2511.04527","title":"Are language models aware of the road not taken? Token-level uncertainty and hidden state dynamics","created":"2025-11-06","cited_by_count":11,"area":"lr"},{"id":"2506.22638","title":"Layer Importance for Mathematical Reasoning is Forged in Pre-Training and Invariant after Post-Training","created":"2025-06-27","cited_by_count":9,"area":"lr"},{"id":"2512.11949","title":"Neural Chameleons: Language Models Can Learn to Hide Their Thoughts from Unseen Activation Monitors","created":"2025-12-12","cited_by_count":9,"area":"lr"},{"id":"2506.15647","title":"Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement","created":"2025-06-18","cited_by_count":8,"area":"lr"},{"id":"2601.08427","title":"Silence the Judge: Reinforcement Learning with Self-Verifier via Latent Geometric Clustering","created":"2026-01-13","cited_by_count":7,"area":"lr"},{"id":"2606.02907","title":"Linear Probes Detect Task Format, Not Reasoning Mode in Language Model Hidden States","created":"2026-06-01","cited_by_count":7,"area":"lr"},{"id":"2601.09269","title":"RISER: Orchestrating Latent Reasoning Skills for Adaptive Activation Steering","created":"2026-01-14","cited_by_count":6,"area":"lr"},{"id":"2603.01437","title":"Post-Hoc Reasoning in Chain of Thought: Decoding and Steering Pre-Committed Answers","created":"2026-03-02","cited_by_count":6,"area":"lr"},{"id":"2603.17199","title":"Catching rationalization in the act: detecting motivated reasoning before and after CoT via activation probing","created":"2026-03-17","cited_by_count":6,"area":"lr"},{"id":"2605.05980","title":"TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering","created":"2026-05-07","cited_by_count":6,"area":"lr"},{"id":"2410.01545","title":"Lines of Thought in Large Language Models","created":"2024-10-02","cited_by_count":5,"area":"lr"},{"id":"2509.11536","title":"HARP: Hallucination Detection via Reasoning Subspace Projection","created":"2025-09-15","cited_by_count":5,"area":"lr"},{"id":"2512.23988","title":"Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning Process","created":"2025-12-30","cited_by_count":5,"area":"lr"},{"id":"2601.02170","title":"Streaming Hallucination Detection in Long Chain-of-Thought Reasoning","created":"2026-01-05","cited_by_count":5,"area":"lr"},{"id":"2604.24881","title":"Latent Agents: A Post-Training Procedure for Internalized Multi-Agent Debate","created":"2026-04-27","cited_by_count":5,"area":"lr"},{"id":"2605.18549","title":"Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics","created":"2026-05-18","cited_by_count":5,"area":"lr"},{"id":"2412.12841","title":"Benchmarking and Understanding Compositional Relational Reasoning of LLMs","created":"2024-12-17","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":"2602.01982","title":"S3-CoT: Self-Sampled Succinct Reasoning Enables Efficient Chain-of-Thought LLMs","created":"2026-02-02","cited_by_count":4,"area":"lr"},{"id":"2507.03167","title":"Where Do Reasoning Models Refuse?","created":"2025-07-03","cited_by_count":3,"area":"lr"},{"id":"2508.18760","title":"Answering the Unanswerable Is to Err Knowingly: Analyzing and Mitigating Abstention Failures in Large Reasoning Models","created":"2025-08-26","cited_by_count":3,"area":"lr"},{"id":"2512.01909","title":"Latent Debate: A Surrogate Framework for Interpreting LLM Thinking","created":"2025-12-01","cited_by_count":3,"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":"2603.14636","title":"Nudging Hidden States: Training-Free Model Steering for Chain-of-Thought Reasoning in Large Audio-Language Models","created":"2026-03-15","cited_by_count":2,"area":"lr"},{"id":"2604.10219","title":"Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models","created":"2026-04-11","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":"2605.11746","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":"2606.17478","title":"Decoding Hidden Deception in Reasoning LLMs: Activation Explainers for Deception Auditing","created":"2026-06-16","cited_by_count":2,"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":"2605.14358","title":"Uncovering the Representation Geometry of Minimal Cores in Overcomplete Reasoning Traces","created":"2026-05-14","cited_by_count":1,"area":"lr"},{"id":"2605.29087","title":"The Chain Holds, the Answer Folds: Trace-Answer Dissociation in Reasoning Models Under Adversarial Pressure","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2606.28589","title":"Search for Truth from Reasoning: A Dynamic Representation Editing Framework for Steering LLM Trajectories","created":"2026-06-26","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":"2609.09030","title":"Answer-Distribution Trajectories: A Stochastic-Dynamics View of LLM Reasoning","created":"2026-09-08","cited_by_count":1,"area":"lr"},{"id":"2601.08846","title":"Directional Attractors in LLM Reasoning: How Similarity Retrieval Steers Iterative Summarization Based Reasoning","created":"2025-12-22","cited_by_count":0,"area":"lr"},{"id":"2606.08571","title":"Calibration of Structured Ignorance Certificates for Diagnosing Unknown Unknowns in Reasoning Models","created":"2026-06-07","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":"2608.04928","title":"Does Out-of-Sight Equal Out-of-Mind in CoT Monitorability?","created":"2026-08-05","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":"2608.18628","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":"2608.29431","title":"Evaluating the Semantic Specificity of Representation Steering in Language Models","created":"2026-08-29","cited_by_count":0,"area":"lr"},{"id":"2608.30650","title":"Geometry of Divergence: Tracking Hidden-State Trajectories for Adaptive Multi-Turn Reasoning","created":"2026-08-31","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":"2609.28442","title":"Order-Invariant Answers, Order-Sensitive Representations in Mathematical Reasoning","created":"2026-09-23","cited_by_count":0,"area":"lr"},{"id":"2609.28682","title":"Thinking Leakage: A Causal Audit of NoThink Post-Training in Hybrid Reasoning Models","created":"2026-09-23","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":"2609.35486","title":"Who Is Left of Whom? Tracing Spatial Evidence and Role Binding in Relative-Position Reasoning","created":"2026-09-28","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":"2610.05472","title":"Hallucination Across the Reasoning Lifecycle: Interface Visibility, Causal Evidence, and Release Control in Large Reasoning Models","created":"2026-10-04","cited_by_count":0,"area":"lr"}],"next_cursor":null}