{"total":54,"rows":[{"id":"2307.02477","title":"Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks","created":"2023-07-05","cited_by_count":246,"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":"2410.21272","title":"Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics","created":"2024-10-28","cited_by_count":97,"area":"lr"},{"id":"2402.18312","title":"How to think step-by-step: A mechanistic understanding of chain-of-thought reasoning","created":"2024-02-28","cited_by_count":53,"area":"lr"},{"id":"2310.14491","title":"Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models","created":"2023-10-23","cited_by_count":50,"area":"lr"},{"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":"2301.06627","title":"Dissociating language and thought in large language models","created":"2023-01-16","cited_by_count":29,"area":"lr"},{"id":"2505.12189","title":"Mitigating Content Effects on Reasoning in Language Models through Fine-Grained Activation Steering","created":"2025-05-18","cited_by_count":18,"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":"2507.01551","title":"Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning","created":"2025-07-02","cited_by_count":11,"area":"lr"},{"id":"2311.18812","title":"What Do Llamas Really Think? Revealing Preference Biases in Language Model Representations","created":"2023-11-30","cited_by_count":10,"area":"lr"},{"id":"2402.18023","title":"Do Large Language Models Mirror Cognitive Language Processing?","created":"2024-02-28","cited_by_count":9,"area":"lr"},{"id":"2605.12671","title":"All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs","created":"2026-05-12","cited_by_count":9,"area":"lr"},{"id":"2604.06374","title":"The Illusion of Superposition? A Principled Analysis of Latent Thinking in Language Models","created":"2026-04-07","cited_by_count":7,"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":"2406.09464","title":"GPT-ology, Computational Models, Silicon Sampling: How should we think about LLMs in Cognitive Science?","created":"2024-06-13","cited_by_count":5,"area":"lr"},{"id":"2512.10978","title":"Cognitive Mirrors: Exploring the Diverse Functional Roles of Attention Heads in LLM Reasoning","created":"2025-12-03","cited_by_count":5,"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":"2601.03542","title":"Layer-Order Inversion: Rethinking Latent Multi-Hop Reasoning in Large Language Models","created":"2026-01-07","cited_by_count":3,"area":"lr"},{"id":"2312.11720","title":"Assessing Logical Reasoning Capabilities of Encoder-Only Transformer Models","created":"2023-12-18","cited_by_count":2,"area":"lr"},{"id":"2512.10300","title":"Investigating The Functional Roles of Attention Heads in Vision Language Models: Evidence for Reasoning Modules","created":"2025-12-11","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":"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":"2606.13106","title":"Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning","created":"2026-06-11","cited_by_count":2,"area":"lr"},{"id":"2606.25354","title":"Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing","created":"2026-06-24","cited_by_count":2,"area":"lr"},{"id":"2606.31257","title":"Decodable Is Not Grounded: A Vision-Ablation Arbiter for VLM Spatial Reasoning","created":"2026-06-30","cited_by_count":2,"area":"lr"},{"id":"2607.08046","title":"What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness","created":"2026-07-09","cited_by_count":2,"area":"lr"},{"id":"2406.12620","title":"What Makes Two Language Models Think Alike?","created":"2024-06-18","cited_by_count":1,"area":"lr"},{"id":"2509.06998","title":"Not All Splits Are Equal: Rethinking Attribute Generalization Across Unrelated Categories","created":"2025-09-04","cited_by_count":1,"area":"lr"},{"id":"2510.09340","title":"Deductive Logic in Language Models: Horizontal vs Vertical Reasoning","created":"2025-10-10","cited_by_count":1,"area":"lr"},{"id":"2603.16017","title":"Understanding Moral Reasoning Trajectories in Large Language Models: Toward Probing-Based Explainability","created":"2026-03-16","cited_by_count":1,"area":"lr"},{"id":"2603.20406","title":"Thinking in Different Spaces: Domain-Specific Latent Geometry Survives Cross-Architecture Translation","created":"2026-03-20","cited_by_count":1,"area":"lr"},{"id":"2605.11906","title":"YFPO: Yoked Feature Preference Optimization with Neuron-Guided Rewards","created":"2026-05-12","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":"2605.31561","title":"What Am I Missing? Question-Answering as Hidden State Probing","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2606.05753","title":"Cosine Misleads: Auxiliary Losses Reshape Vision Language Models, Not Their Latents","created":"2026-06-04","cited_by_count":1,"area":"lr"},{"id":"2607.23458","title":"Two Regimes of Chain-of-Thought Unfaithfulness: Metric-Based Detection Fails Where Models Are Wrong","created":"2026-07-26","cited_by_count":1,"area":"lr"},{"id":"2508.13408","title":"NovoMolGen: Rethinking Molecular Language Model Pretraining","created":"2025-08-19","cited_by_count":0,"area":"lr"},{"id":"2510.08613","title":"GraphGhost: Tracing Structures Behind Large Language Models","created":"2025-10-07","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":"2605.28825","title":"MechELK: A Mechanistic Interpretability Framework for Eliciting Latent Knowledge in Large Language Models","created":"2026-04-07","cited_by_count":0,"area":"lr"},{"id":"2606.03234","title":"Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning","created":"2026-06-02","cited_by_count":0,"area":"lr"},{"id":"2607.06445","title":"Analysis-by-Proxy: Localization Signals in VLMs Operating as Condition Encoders","created":"2026-07-07","cited_by_count":0,"area":"lr"},{"id":"2607.13899","title":"AIMO Interpretability Challenge","created":"2026-07-15","cited_by_count":0,"area":"lr"},{"id":"2607.16094","title":"How Do VLMs Fail? Vision-Operation Misalignment in Compositional VQA","created":"2026-07-17","cited_by_count":0,"area":"lr"},{"id":"2608.30751","title":"Autoregressive Mosaics: Probing 2D Spatial Reasoning in Text-Only Language Models","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":"2609.00764","title":"Are You Thinking What I am Thinking? : Examining Conceptual Separation in Neural Architectures","created":"2026-09-01","cited_by_count":0,"area":"lr"},{"id":"2609.29278","title":"Reasoning Instructions Can Break Answer Decoding in Vision--Language Models","created":"2026-09-24","cited_by_count":0,"area":"lr"},{"id":"2609.34809","title":"From Perception to Integration: Revisiting the Internal Dynamics of Reasoning in Vision-Language Models","created":"2026-09-28","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":"2610.05715","title":"Rotated, but How Far? Diagnosing and Improving Object-Rotation Reasoning in VLMs","created":"2026-10-05","cited_by_count":0,"area":"lr"}],"next_cursor":null}