{"total":162,"rows":[{"id":"2402.08787","title":"Rethinking Machine Unlearning for Large Language Models","created":"2024-02-13","cited_by_count":257,"area":"lr"},{"id":"2403.17887","title":"The Unreasonable Ineffectiveness of the Deeper Layers","created":"2024-03-26","cited_by_count":226,"area":"lr"},{"id":"2310.16218","title":"Knowledge Editing for Large Language Models: A Survey","created":"2023-10-24","cited_by_count":194,"area":"lr"},{"id":"2402.16837","title":"Do Large Language Models Latently Perform Multi-Hop Reasoning?","created":"2024-02-26","cited_by_count":169,"area":"lr"},{"id":"2312.13558","title":"The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction","created":"2023-12-21","cited_by_count":123,"area":"lr"},{"id":"2402.05602","title":"AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers","created":"2024-02-08","cited_by_count":120,"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":"2307.09476","title":"Overthinking the Truth: Understanding how Language Models Process False Demonstrations","created":"2023-07-18","cited_by_count":81,"area":"lr"},{"id":"2405.15071","title":"Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization","created":"2024-05-23","cited_by_count":79,"area":"lr"},{"id":"2502.15603","title":"Do Multilingual LLMs Think In English?","created":"2025-02-21","cited_by_count":78,"area":"lr"},{"id":"2311.11797","title":"Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents","created":"2023-11-20","cited_by_count":72,"area":"lr"},{"id":"2506.18167","title":"Understanding Reasoning in Thinking Language Models via Steering Vectors","created":"2025-06-22","cited_by_count":72,"area":"lr"},{"id":"2210.12023","title":"A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models","created":"2022-10-21","cited_by_count":68,"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":"2502.14829","title":"Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps","created":"2025-02-20","cited_by_count":47,"area":"lr"},{"id":"2411.02280","title":"The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant Units","created":"2024-11-04","cited_by_count":34,"area":"lr"},{"id":"2401.10471","title":"DeepEdit: Knowledge Editing as Decoding with Constraints","created":"2024-01-19","cited_by_count":33,"area":"lr"},{"id":"2409.09822","title":"Causal Inference with Large Language Model: A Survey","created":"2024-09-15","cited_by_count":32,"area":"lr"},{"id":"2502.20332","title":"Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models","created":"2025-02-27","cited_by_count":31,"area":"lr"},{"id":"2411.16679","title":"Do Large Language Models Perform Latent Multi-Hop Reasoning without Exploiting Shortcuts?","created":"2024-11-25","cited_by_count":28,"area":"lr"},{"id":"2507.02199","title":"Latent Chain-of-Thought? Decoding the Depth-Recurrent Transformer","created":"2025-07-02","cited_by_count":27,"area":"lr"},{"id":"2507.04742","title":"Activation Steering for Chain-of-Thought Compression","created":"2025-07-07","cited_by_count":24,"area":"lr"},{"id":"2312.15194","title":"PokeMQA: Programmable knowledge editing for Multi-hop Question Answering","created":"2023-12-23","cited_by_count":23,"area":"lr"},{"id":"2510.00553","title":"On Predictability of Reinforcement Learning Dynamics for Large Language Models","created":"2025-10-01","cited_by_count":23,"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":"2309.05605","title":"Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models","created":"2023-09-11","cited_by_count":21,"area":"lr"},{"id":"2502.13913","title":"How Do LLMs Perform Two-Hop Reasoning in Context?","created":"2025-02-19","cited_by_count":20,"area":"lr"},{"id":"2305.06349","title":"RECKONING: Reasoning through Dynamic Knowledge Encoding","created":"2023-05-10","cited_by_count":18,"area":"lr"},{"id":"2411.16353","title":"Lessons from Studying Two-Hop Latent Reasoning","created":"2024-11-25","cited_by_count":17,"area":"lr"},{"id":"2405.15302","title":"Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer Mechanism","created":"2024-05-24","cited_by_count":15,"area":"lr"},{"id":"2507.10616","title":"Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them","created":"2025-07-13","cited_by_count":15,"area":"lr"},{"id":"2402.11900","title":"Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language Models","created":"2024-02-19","cited_by_count":14,"area":"lr"},{"id":"2409.14026","title":"Uncovering Latent Chain of Thought Vectors in Language Models","created":"2024-09-21","cited_by_count":14,"area":"lr"},{"id":"2502.20377","title":"PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation","created":"2025-02-27","cited_by_count":14,"area":"lr"},{"id":"2503.07604","title":"Implicit Reasoning in Transformers is Reasoning through Shortcuts","created":"2025-03-10","cited_by_count":14,"area":"lr"},{"id":"2601.11061","title":"Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs","created":"2026-01-16","cited_by_count":14,"area":"lr"},{"id":"2508.20279","title":"How Multimodal LLMs Solve Image Tasks: A Lens on Visual Grounding, Task Reasoning, and Answer Decoding","created":"2025-08-27","cited_by_count":13,"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":"2602.08783","title":"Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure","created":"2026-02-09","cited_by_count":11,"area":"lr"},{"id":"2603.08391","title":"Adaptive Loops and Memory in Transformers: Think Harder or Know More?","created":"2026-03-09","cited_by_count":11,"area":"lr"},{"id":"2410.13194","title":"The Geometry of Numerical Reasoning: Language Models Compare Numeric Properties in Linear Subspaces","created":"2024-10-17","cited_by_count":10,"area":"lr"},{"id":"2502.04667","title":"Compositional Generalization from Learned Skills via CoT Training: A Theoretical and Structural Analysis for Reasoning","created":"2025-02-07","cited_by_count":10,"area":"lr"},{"id":"2505.10039","title":"Rethinking Circuit Completeness in Language Models: AND, OR, and ADDER Gates","created":"2025-05-15","cited_by_count":10,"area":"lr"},{"id":"2509.24156","title":"Reasoning or Retrieval? A Study of Answer Attribution on Large Reasoning Models","created":"2025-09-29","cited_by_count":10,"area":"lr"},{"id":"2505.08140","title":"Lost in Transmission: When and Why LLMs Fail to Reason Globally","created":"2025-05-13","cited_by_count":9,"area":"lr"},{"id":"2510.10494","title":"Tracing the Traces: Latent Temporal Signals for Efficient and Accurate Reasoning","created":"2025-10-12","cited_by_count":9,"area":"lr"},{"id":"2602.11201","title":"Mechanistic Evidence for Faithfulness Decay in Chain-of-Thought Reasoning","created":"2026-02-04","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":"2505.23701","title":"Can LLMs Reason Abstractly Over Math Word Problems Without CoT? Disentangling Abstract Formulation From Arithmetic Computation","created":"2025-05-29","cited_by_count":8,"area":"lr"},{"id":"2508.08833","title":"An Investigation of Robustness of LLMs in Mathematical Reasoning: Benchmarking with Mathematically-Equivalent Transformation of Advanced Mathematical Problems","created":"2025-08-12","cited_by_count":8,"area":"lr"},{"id":"2509.01544","title":"Causal Consistency Regularization: Training Verifiably Sensitive Reasoning in Large Language Models","created":"2025-09-01","cited_by_count":8,"area":"lr"},{"id":"2602.20330","title":"Circuit Tracing in Vision-Language Models: Understanding the Internal Mechanisms of Multimodal Thinking","created":"2026-02-23","cited_by_count":8,"area":"lr"},{"id":"2503.09620","title":"Exploiting Edited Large Language Models as General Scientific Optimizers","created":"2025-03-08","cited_by_count":7,"area":"lr"},{"id":"2601.15495","title":"Tracking the Limits of Knowledge Propagation: How LLMs Fail at Multi-Step Reasoning with Conflicting Knowledge","created":"2026-01-21","cited_by_count":7,"area":"lr"},{"id":"2602.09331","title":"Beyond Uniform Credit: Causal Credit Assignment for Policy Optimization","created":"2026-02-10","cited_by_count":7,"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":"2605.13156","title":"Dual-Pathway Circuits of Object Hallucination in Vision-Language Models","created":"2026-05-13","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":"2607.26760","title":"Metis: Memory Foundation Model","created":"2026-07-29","cited_by_count":7,"area":"lr"},{"id":"2602.24014","title":"Interpretable Debiasing of Vision-Language Models for Social Fairness","created":"2026-02-27","cited_by_count":6,"area":"lr"},{"id":"2605.28732","title":"MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems","created":"2026-05-27","cited_by_count":6,"area":"lr"},{"id":"2312.03633","title":"Exploring the Reversal Curse and Other Deductive Logical Reasoning in BERT and GPT-Based Large Language Models","created":"2023-12-06","cited_by_count":5,"area":"lr"},{"id":"2410.03122","title":"RIPPLECOT: Amplifying Ripple Effect of Knowledge Editing in Language Models via Chain-of-Thought In-Context Learning","created":"2024-10-04","cited_by_count":5,"area":"lr"},{"id":"2506.21590","title":"Representation Consistency for Accurate and Coherent LLM Answer Aggregation","created":"2025-06-18","cited_by_count":5,"area":"lr"},{"id":"2507.18178","title":"Decoupling Knowledge and Reasoning in LLMs: An Exploration Using Cognitive Dual-System Theory","created":"2025-07-24","cited_by_count":5,"area":"lr"},{"id":"2509.22518","title":"REMA: A Unified Reasoning Manifold Framework for Interpreting Large Language Model","created":"2025-09-26","cited_by_count":5,"area":"lr"},{"id":"2604.08016","title":"Wiring the 'Why': A Unified Taxonomy and Survey of Abductive Reasoning in LLMs","created":"2026-04-09","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":"2410.10584","title":"STACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with FeedBack","created":"2024-10-14","cited_by_count":4,"area":"lr"},{"id":"2502.04030","title":"Fine, I'll Merge It Myself: A Multi-Fidelity Framework for Automated Model Merging","created":"2025-02-06","cited_by_count":4,"area":"lr"},{"id":"2504.10077","title":"Towards Quantifying Commonsense Reasoning with Mechanistic Insights","created":"2025-04-14","cited_by_count":4,"area":"lr"},{"id":"2504.12637","title":"Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation","created":"2025-04-17","cited_by_count":4,"area":"lr"},{"id":"2506.01386","title":"ThinkEval: Practical Evaluation of Knowledge Leakage in LLM Editing using Thought-based Knowledge Graphs","created":"2025-06-02","cited_by_count":4,"area":"lr"},{"id":"2509.01363","title":"Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic","created":"2025-09-01","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":"2601.10229","title":"GeoSteer: Faithful Chain-of-Thought Steering via Latent Manifold Gradients","created":"2026-01-15","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":"2602.06453","title":"On the Plasticity and Stability for Post-Training Large Language Models","created":"2026-02-06","cited_by_count":4,"area":"lr"},{"id":"2605.14075","title":"Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity","created":"2026-05-13","cited_by_count":4,"area":"lr"},{"id":"2510.06052","title":"MixReasoning: Switching Modes to Think","created":"2025-10-07","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":"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":"2601.04878","title":"Higher-Order Knowledge Representations for Agentic Scientific Reasoning","created":"2026-01-08","cited_by_count":3,"area":"lr"},{"id":"2601.05144","title":"Distilling the Thought, Watermarking the Answer: A Principle Semantic Guided Watermark for Large Reasoning Models","created":"2026-01-08","cited_by_count":3,"area":"lr"},{"id":"2603.03475","title":"When Shallow Wins: Silent Failures and the Depth-Accuracy Paradox in Latent Reasoning","created":"2026-03-03","cited_by_count":3,"area":"lr"},{"id":"2603.18523","title":"Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language Models","created":"2026-03-19","cited_by_count":3,"area":"lr"},{"id":"2606.01243","title":"Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention","created":"2026-05-31","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":"2606.19172","title":"User as Engram: Internalizing Per-User Memory as Local Parametric Edits","created":"2026-06-17","cited_by_count":3,"area":"lr"},{"id":"2305.14507","title":"Deduction under Perturbed Evidence: Probing Student Simulation Capabilities of Large Language Models","created":"2023-05-23","cited_by_count":2,"area":"lr"},{"id":"2504.10646","title":"Weight-of-Thought Reasoning: Exploring Neural Network Weights for Enhanced LLM Reasoning","created":"2025-04-14","cited_by_count":2,"area":"lr"},{"id":"2508.10057","title":"Large Language Models Show Signs of Alignment with Human Neurocognition During Abstract Reasoning","created":"2025-08-12","cited_by_count":2,"area":"lr"},{"id":"2510.24256","title":"From Memorization to Reasoning in the Spectrum of Loss Curvature","created":"2025-10-28","cited_by_count":2,"area":"lr"},{"id":"2602.04556","title":"Rethinking Weight Tying: Pseudo-Inverse Tying for LM Stable Training and Updates","created":"2026-02-04","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":"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":"2605.13772","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":"2606.04889","title":"GRAIL: Gradient-Reweighted Advantages for Reinforcement Learning with Verifiable Rewards","created":"2026-06-03","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"}],"next_cursor":"100"}