{"total":37,"rows":[{"id":"2310.06824","title":"The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets","created":"2023-10-10","cited_by_count":712,"area":null},{"id":"2305.13172","title":"Editing Large Language Models: Problems, Methods, and Opportunities","created":"2023-05-22","cited_by_count":372,"area":null},{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334,"area":null},{"id":"2310.15213","title":"Function Vectors in Large Language Models","created":"2023-10-23","cited_by_count":308,"area":null},{"id":"2301.04213","title":"Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models","created":"2023-01-10","cited_by_count":243,"area":null},{"id":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163,"area":null},{"id":"2302.06600","title":"Task-Specific Skill Localization in Fine-tuned Language Models","created":"2023-02-13","cited_by_count":105,"area":null},{"id":"2402.03804","title":"ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs","created":"2024-02-06","cited_by_count":67,"area":null},{"id":"2305.18390","title":"Emergent Modularity in Pre-trained Transformers","created":"2023-05-28","cited_by_count":37,"area":null},{"id":"2309.07418","title":"A Fast Optimization View: Reformulating Single Layer Attention in LLM Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time","created":"2023-09-14","cited_by_count":30,"area":null},{"id":"2401.12200","title":"APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference","created":"2024-01-22","cited_by_count":29,"area":null},{"id":"2308.10502","title":"GradientCoin: A Peer-to-Peer Decentralized Large Language Models","created":"2023-08-21","cited_by_count":23,"area":null},{"id":"2410.04045","title":"Neuron-Level Sequential Editing for Large Language Models","created":"2024-10-05","cited_by_count":20,"area":null},{"id":"2405.09341","title":"Large Language Model Bias Mitigation from the Perspective of Knowledge Editing","created":"2024-05-15","cited_by_count":16,"area":null},{"id":"2310.18443","title":"Towards a fuller understanding of neurons with Clustered Compositional Explanations","created":"2023-10-27","cited_by_count":15,"area":null},{"id":"2406.11828","title":"Learning sum of diverse features: computational hardness and efficient gradient-based training for ridge combinations","created":"2024-06-17","cited_by_count":13,"area":null},{"id":"2502.05390","title":"Learning Task Representations from In-Context Learning","created":"2025-02-08","cited_by_count":11,"area":null},{"id":"2504.07440","title":"Model Utility Law: Evaluating LLMs beyond Performance through Mechanism Interpretable Metric","created":"2025-04-10","cited_by_count":11,"area":null},{"id":"2301.12608","title":"Evaluating Neuron Interpretation Methods of NLP Models","created":"2023-01-30","cited_by_count":8,"area":null},{"id":"2310.20051","title":"The Expressibility of Polynomial based Attention Scheme","created":"2023-10-30","cited_by_count":7,"area":null},{"id":"2302.09582","title":"Language-Specific Representation of Emotion-Concept Knowledge Causally Supports Emotion Inference","created":"2023-02-19","cited_by_count":6,"area":null},{"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":"2409.05910","title":"Property Neurons in Self-Supervised Speech Transformers","created":"2024-09-07","cited_by_count":5,"area":null},{"id":"2502.20408","title":"Brain-Inspired Exploration of Functional Networks and Key Neurons in Large Language Models","created":"2025-02-13","cited_by_count":5,"area":null},{"id":"2502.20779","title":"Triple Phase Transitions: Understanding the Learning Dynamics of Large Language Models from a Neuroscience Perspective","created":"2025-02-28","cited_by_count":4,"area":null},{"id":"2305.08732","title":"Knowledge Rumination for Pre-trained Language Models","created":"2023-05-15","cited_by_count":2,"area":null},{"id":"2309.12263","title":"On the Relationship between Skill Neurons and Robustness in Prompt Tuning","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2405.06003","title":"Binary Hypothesis Testing for Softmax Models and Leverage Score Models","created":"2024-05-09","cited_by_count":1,"area":null},{"id":"2406.02021","title":"FFNet: MetaMixer-based Efficient Convolutional Mixer Design","created":"2024-06-04","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":"2510.13580","title":"Sparse Subnetwork Enhancement for Underrepresented Languages in Large Language Models","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2406.15996","title":"Memorizing Documents with Guidance in Large Language Models","created":"2024-06-23","cited_by_count":0,"area":null},{"id":"2607.07128","title":"Distributed Sparse Interventions in Language Models","created":"2026-07-08","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":"2608.10214","title":"Decodable But Not Detachable: Training Data Granularity Determines Parametric Modularity in Large Language Models","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.28250","title":"Complementary Roles of Activation and Parametric Memory in Few-Shot Learning","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2610.05161","title":"Beyond Instruction Following: Learning Grounded Skill-Following with Skill Contracts","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}