{"total":66,"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":"2212.09597","title":"Reasoning with Language Model Prompting: A Survey","created":"2022-12-19","cited_by_count":252,"area":"lr"},{"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":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231,"area":"alignment"},{"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":"2407.02646","title":"A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models","created":"2024-07-02","cited_by_count":118,"area":"mechinterp"},{"id":"2302.06600","title":"Task-Specific Skill Localization in Fine-tuned Language Models","created":"2023-02-13","cited_by_count":105,"area":null},{"id":"2401.12181","title":"Universal Neurons in GPT2 Language Models","created":"2024-01-22","cited_by_count":102,"area":"mechinterp"},{"id":"2306.03745","title":"Soft Merging of Experts with Adaptive Routing","created":"2023-06-06","cited_by_count":90,"area":"moe"},{"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":"2405.19237","title":"ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning","created":"2024-05-29","cited_by_count":55,"area":"diffusion"},{"id":"2406.14144","title":"Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons","created":"2024-06-20","cited_by_count":53,"area":"alignment"},{"id":"2406.03445","title":"Pre-trained Large Language Models Use Fourier Features to Compute Addition","created":"2024-06-05","cited_by_count":39,"area":"lr"},{"id":"2305.18390","title":"Emergent Modularity in Pre-trained Transformers","created":"2023-05-28","cited_by_count":37,"area":null},{"id":"2504.04633","title":"M$^2$IV: Towards Efficient and Fine-grained Multimodal In-Context Learning via Representation Engineering","created":"2025-04-06","cited_by_count":35,"area":"mllm"},{"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":"2406.12288","title":"An Investigation of Neuron Activation as a Unified Lens to Explain Chain-of-Thought Eliciting Arithmetic Reasoning of LLMs","created":"2024-06-18","cited_by_count":20,"area":"lr"},{"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":"2502.16368","title":"Concept Corrector: Erase concepts on the fly for text-to-image diffusion models","created":"2025-02-22","cited_by_count":11,"area":"diffusion"},{"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":"2502.16690","title":"From Text to Space: Mapping Abstract Spatial Models in LLMs during a Grid-World Navigation Task","created":"2025-02-23","cited_by_count":10,"area":"agents"},{"id":"2301.12608","title":"Evaluating Neuron Interpretation Methods of NLP Models","created":"2023-01-30","cited_by_count":8,"area":null},{"id":"2306.01117","title":"Examining the Causal Effect of First Names on Language Models: The Case of Social Commonsense Reasoning","created":"2023-06-01","cited_by_count":8,"area":"lr"},{"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":"2602.22554","title":"Multilingual Safety Alignment Via Sparse Weight Editing","created":"2026-02-26","cited_by_count":6,"area":"alignment"},{"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":"2310.15477","title":"CRaSh: Clustering, Removing, and Sharing Enhance Fine-tuning without Full Large Language Model","created":"2023-10-24","cited_by_count":5,"area":"alignment"},{"id":"2409.05910","title":"Property Neurons in Self-Supervised Speech Transformers","created":"2024-09-07","cited_by_count":5,"area":null},{"id":"2410.03440","title":"Exploring the Benefit of Activation Sparsity in Pre-training","created":"2024-10-04","cited_by_count":5,"area":"moe"},{"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":"2509.22263","title":"Erase or Hide? Suppressing Spurious Unlearning Neurons for Robust Unlearning","created":"2025-09-26","cited_by_count":5,"area":"safety"},{"id":"2310.05442","title":"Establishing Trustworthiness: Rethinking Tasks and Model Evaluation","created":"2023-10-09","cited_by_count":4,"area":"lr"},{"id":"2311.15759","title":"Vision Enhancing LLMs: Empowering Multimodal Knowledge Storage and Sharing in LLMs","created":"2023-11-27","cited_by_count":4,"area":"mllm"},{"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":"2503.22941","title":"Identifying Multi-modal Knowledge Neurons in Pretrained Transformers via Two-stage Filtering","created":"2025-03-29","cited_by_count":3,"area":"mllm"},{"id":"2510.02296","title":"Continual Personalization for Diffusion Models","created":"2025-10-02","cited_by_count":3,"area":"diffusion"},{"id":"2602.19058","title":"Do LLMs and VLMs Share Neurons for Inference? Evidence and Mechanisms of Cross-Modal Transfer","created":"2026-02-22","cited_by_count":3,"area":"mllm"},{"id":"2606.02398","title":"A Local Perturbation Theory for Cross-Domain Interference and Recovery in Multi-Domain RL","created":"2026-06-01","cited_by_count":3,"area":"lr"},{"id":"2305.08732","title":"Knowledge Rumination for Pre-trained Language Models","created":"2023-05-15","cited_by_count":2,"area":null},{"id":"2604.13694","title":"Weight Patching: Toward Source-Level Mechanistic Localization in LLMs","created":"2026-04-15","cited_by_count":2,"area":"mechinterp"},{"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":"2507.18512","title":"Explaining How Visual, Textual and Multimodal Encoders Share Concepts","created":"2025-07-24","cited_by_count":1,"area":"mechinterp"},{"id":"2510.02528","title":"Multimodal Function Vectors for Visual Relations","created":"2025-10-02","cited_by_count":1,"area":"mllm"},{"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":"2504.08000","title":"Neuron-level Balance between Stability and Plasticity in Deep Reinforcement Learning","created":"2025-04-09","cited_by_count":0,"area":"deeprl"},{"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":"2609.29781","title":"Hallucination Neurons and Where to Find Them: An Investigation into the existence of Hallucination Neurons","created":"2026-09-24","cited_by_count":0,"area":"alignment"},{"id":"2609.34475","title":"Causal Routing for Unlearning","created":"2026-09-28","cited_by_count":0,"area":"safety"},{"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}