{"total":60,"rows":[{"id":"2409.03752","title":"Attention Heads of Large Language Models: A Survey","created":"2024-09-05","cited_by_count":67,"area":null},{"id":"2502.19301","title":"Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond","created":"2025-02-26","cited_by_count":61,"area":"lr"},{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"area":null},{"id":"2410.16251","title":"Can Knowledge Editing Really Correct Hallucinations?","created":"2024-10-21","cited_by_count":28,"area":null},{"id":"2601.14004","title":"Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models","created":"2026-01-20","cited_by_count":27,"area":"mechinterp"},{"id":"2502.11196","title":"How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training","created":"2025-02-16","cited_by_count":23,"area":null},{"id":"2410.01380","title":"Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition","created":"2024-10-02","cited_by_count":16,"area":null},{"id":"2506.01115","title":"Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer","created":"2025-06-01","cited_by_count":12,"area":"lr"},{"id":"2502.09022","title":"Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning","created":"2025-02-13","cited_by_count":11,"area":"lr"},{"id":"2602.16823","title":"Formal Mechanistic Interpretability: Automated Circuit Discovery with Provable Guarantees","created":"2026-02-18","cited_by_count":11,"area":"mechinterp"},{"id":"2501.12976","title":"LiT: Delving into a Simple Linear Diffusion Transformer for Image Generation","created":"2025-01-22","cited_by_count":10,"area":"diffusion"},{"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":"2605.06510","title":"Is One Layer Enough? Understanding Inference Dynamics in Tabular Foundation Models","created":"2026-05-07","cited_by_count":10,"area":null},{"id":"2502.14838","title":"Revealing and Mitigating Over-Attention in Knowledge Editing","created":"2025-02-20","cited_by_count":8,"area":null},{"id":"2505.21701","title":"Do We Know What LLMs Don't Know? A Study of Consistency in Knowledge Probing","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2509.25758","title":"Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post Training","created":"2025-09-30","cited_by_count":8,"area":"lr"},{"id":"2509.01631","title":"Unraveling LLM Jailbreaks Through Safety Knowledge Neurons","created":"2025-09-01","cited_by_count":7,"area":"safety"},{"id":"2512.18813","title":"Revealing Perception and Generation Dynamics in LVLMs: Mitigating Hallucinations via Validated Dominance Correction","created":"2025-12-21","cited_by_count":7,"area":"mllm"},{"id":"2506.18141","title":"Sparse Feature Coactivation Reveals Causal Semantic Modules in Large Language Models","created":"2025-06-22","cited_by_count":6,"area":"mechinterp"},{"id":"2604.27707","title":"Contextual Agentic Memory is a Memo, Not True Memory","created":"2026-04-30","cited_by_count":6,"area":"rag"},{"id":"2607.20594","title":"When Does Recurrence Become an Algorithm? Convergence Selection in Weight-Tied Looped Transformers","created":"2026-07-22","cited_by_count":6,"area":null},{"id":"2601.05693","title":"Circular Reasoning: Understanding Self-Reinforcing Loops in Large Reasoning Models","created":"2026-01-09","cited_by_count":5,"area":"lr"},{"id":"2605.05668","title":"Large Vision-Language Models Get Lost in Attention","created":"2026-05-07","cited_by_count":5,"area":"mllm"},{"id":"2505.13515","title":"LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades","created":"2025-05-17","cited_by_count":4,"area":null},{"id":"2603.23268","title":"SafeSeek: Universal Attribution of Safety Circuits in Language Models","created":"2026-03-24","cited_by_count":4,"area":"safety"},{"id":"2410.17714","title":"CogSteer: Cognition-Inspired Selective Layer Intervention for Efficiently Steering Large Language Models","created":"2024-10-23","cited_by_count":3,"area":null},{"id":"2504.20972","title":"SetKE: Knowledge Editing for Knowledge Elements Overlap","created":"2025-04-29","cited_by_count":3,"area":null},{"id":"2509.17866","title":"Understanding Post-Training Structural Changes in Large Language Models","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2604.15701","title":"Improving Reasoning Capabilities in Small Models through Mixture-of-Layers Distillation with Stepwise Attention on Key Information","created":"2026-04-17","cited_by_count":3,"area":"lr"},{"id":"2507.05158","title":"Steering Information Utility in Key-Value Memory for Language Model Post-Training","created":"2025-07-07","cited_by_count":2,"area":null},{"id":"2509.07149","title":"Measuring Uncertainty in Transformer Circuits with Effective Information Consistency","created":"2025-09-08","cited_by_count":2,"area":"mechinterp"},{"id":"2510.11218","title":"The Curious Case of Factual (Mis)Alignment between LLMs' Short- and Long-Form Answers","created":"2025-10-13","cited_by_count":2,"area":null},{"id":"2602.06702","title":"Explaining Grokking in Transformers through the Lens of Inductive Bias","created":"2026-02-06","cited_by_count":2,"area":null},{"id":"2604.17761","title":"Contrastive Attribution in the Wild: An Interpretability Analysis of LLM Failures on Realistic Benchmarks","created":"2026-04-20","cited_by_count":2,"area":"mechinterp"},{"id":"2606.16920","title":"Demystifying Variance in Circuit Discovery of LLMs","created":"2026-06-15","cited_by_count":2,"area":"mechinterp"},{"id":"2410.01334","title":"Skill Path: Unveiling Language Skills from Circuit Graphs","created":"2024-10-02","cited_by_count":1,"area":null},{"id":"2502.20992","title":"Capability Localization: Capabilities Can be Localized rather than Individual Knowledge","created":"2025-02-28","cited_by_count":1,"area":null},{"id":"2505.16178","title":"Understanding Fact Recall in Language Models: Why Two-Stage Training Encourages Memorization but Mixed Training Teaches Knowledge","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2506.22105","title":"Identifying a Circuit for Verb Conjugation in GPT-2","created":"2025-06-27","cited_by_count":1,"area":null},{"id":"2507.04487","title":"LoSiA: Efficient High-Rank Fine-Tuning via Subnet Localization and Optimization","created":"2025-07-06","cited_by_count":1,"area":null},{"id":"2509.18762","title":"When Long Helps Short: How Context Length in Supervised Fine-tuning Affects Behavior of Large Language Models","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2601.03570","title":"How Do Large Language Models Learn Concepts During Continual Pre-Training?","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2603.06923","title":"Reforming the Mechanism: Editing Reasoning Patterns in LLMs with Circuit Reshaping","created":"2026-03-06","cited_by_count":1,"area":"lr"},{"id":"2607.08605","title":"When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities","created":"2026-07-09","cited_by_count":1,"area":"mechinterp"},{"id":"2410.20340","title":"Maintaining Informative Coherence: Migrating Hallucinations in Large Language Models via Absorbing Markov Chains","created":"2024-10-27","cited_by_count":0,"area":null},{"id":"2502.17017","title":"Quantifying Logical Consistency in Transformers via Query-Key Alignment","created":"2025-02-24","cited_by_count":0,"area":"lr"},{"id":"2507.19420","title":"CircuitProbe: Tracing Visual Temporal Evidence Flow in Video Language Models","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2509.20784","title":"Towards Atoms of Large Language Models","created":"2025-09-25","cited_by_count":0,"area":"mechinterp"},{"id":"2510.14825","title":"Programmatic Representation Learning with Language Models","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2511.20302","title":"CrossEarth-Gate: Fisher-Guided Adaptive Tuning Engine for Efficient Adaptation of Cross-Domain Remote Sensing Semantic Segmentation","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2603.05143","title":"Feature Resemblance: Towards a Theoretical Understanding of Analogical Reasoning in Transformers","created":"2026-03-05","cited_by_count":0,"area":"lr"},{"id":"2604.03764","title":"Automated Attention Pattern Discovery at Scale in Large Language Models","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2605.05741","title":"HyperLens: Quantifying Cognitive Effort in LLMs with Fine-grained Confidence Trajectory","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2607.06120","title":"AEGIS: A Mechanism-Guided Defense against Visual Synonym Jailbreaks in Text-to-Image Models","created":"2026-07-07","cited_by_count":0,"area":"diffusion"},{"id":"2607.08393","title":"Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2608.04111","title":"GEB-Bench: Abstract Structures Told in Many Voices","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2609.33183","title":"Identifying Temporal Features within Transcoders for Time Sensitive Factual Recall","created":"2026-09-27","cited_by_count":0,"area":"mechinterp"},{"id":"2609.34449","title":"CORTEX: Learning to Share and Specialize in Dense Language Models","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36813","title":"RESCUE: Repairing Language Model Errors to Sparse Circuits via Reinforcement Learning","created":"2026-09-29","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}