{"total":90,"rows":[{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001,"area":null},{"id":"2304.14767","title":"Dissecting Recall of Factual Associations in Auto-Regressive Language Models","created":"2023-04-28","cited_by_count":528,"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":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163,"area":null},{"id":"2306.00802","title":"Birth of a Transformer: A Memory Viewpoint","created":"2023-06-01","cited_by_count":161,"area":null},{"id":"2307.15771","title":"The Hydra Effect: Emergent Self-repair in Language Model Computations","created":"2023-07-28","cited_by_count":156,"area":null},{"id":"2307.09458","title":"Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla","created":"2023-07-18","cited_by_count":149,"area":null},{"id":"2406.19384","title":"The Remarkable Robustness of LLMs: Stages of Inference?","created":"2024-06-27","cited_by_count":146,"area":null},{"id":"2409.10695","title":"Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models","created":"2024-09-16","cited_by_count":116,"area":null},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2303.09435","title":"Jump to Conclusions: Short-Cutting Transformers With Linear Transformations","created":"2023-03-16","cited_by_count":90,"area":null},{"id":"2310.04625","title":"Copy Suppression: Comprehensively Understanding an Attention Head","created":"2023-10-06","cited_by_count":76,"area":null},{"id":"2309.15098","title":"Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models","created":"2023-09-26","cited_by_count":67,"area":null},{"id":"2406.16254","title":"Confidence Regulation Neurons in Language Models","created":"2024-06-24","cited_by_count":57,"area":null},{"id":"2310.00492","title":"From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning","created":"2023-09-30","cited_by_count":56,"area":null},{"id":"2401.12874","title":"From Understanding to Utilization: A Survey on Explainability for Large Language Models","created":"2024-01-23","cited_by_count":48,"area":null},{"id":"2410.05864","title":"From Tokens to Words: On the Inner Lexicon of LLMs","created":"2024-10-08","cited_by_count":48,"area":null},{"id":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","cited_by_count":46,"area":null},{"id":"2403.01548","title":"In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation","created":"2024-03-03","cited_by_count":45,"area":null},{"id":"2305.12535","title":"Explaining How Transformers Use Context to Build Predictions","created":"2023-05-21","cited_by_count":43,"area":null},{"id":"2410.06331","title":"Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing","created":"2024-10-08","cited_by_count":37,"area":null},{"id":"2407.15018","title":"Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions","created":"2024-07-21","cited_by_count":35,"area":null},{"id":"2310.19704","title":"A Survey on Knowledge Editing of Neural Networks","created":"2023-10-30","cited_by_count":34,"area":null},{"id":"2404.13400","title":"HiVG: Hierarchical Multimodal Fine-grained Modulation for Visual Grounding","created":"2024-04-20","cited_by_count":31,"area":null},{"id":"2405.20612","title":"UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation","created":"2024-05-31","cited_by_count":31,"area":null},{"id":"2212.10380","title":"What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary","created":"2022-12-20","cited_by_count":28,"area":null},{"id":"2310.18969","title":"Analyzing Vision Transformers for Image Classification in Class Embedding Space","created":"2023-10-29","cited_by_count":26,"area":null},{"id":"2409.09951","title":"Optimal ablation for interpretability","created":"2024-09-16","cited_by_count":25,"area":null},{"id":"2308.12462","title":"Overcoming Generic Knowledge Loss with Selective Parameter Update","created":"2023-08-23","cited_by_count":23,"area":null},{"id":"2310.03686","title":"DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers","created":"2023-10-05","cited_by_count":22,"area":null},{"id":"2310.16270","title":"Attention Lens: A Tool for Mechanistically Interpreting the Attention Head Information Retrieval Mechanism","created":"2023-10-25","cited_by_count":22,"area":null},{"id":"2404.07004","title":"LM Transparency Tool: Interactive Tool for Analyzing Transformer Language Models","created":"2024-04-10","cited_by_count":16,"area":null},{"id":"2511.06876","title":"Generating an Image From 1,000 Words: Enhancing Text-to-Image With Structured Captions","created":"2025-11-10","cited_by_count":14,"area":null},{"id":"2312.01648","title":"Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation","created":"2023-12-04","cited_by_count":12,"area":null},{"id":"2405.14880","title":"Dissecting Query-Key Interaction in Vision Transformers","created":"2024-04-04","cited_by_count":12,"area":null},{"id":"2510.15804","title":"Emergence of Linear Truth Encodings in Language Models","created":"2025-10-17","cited_by_count":12,"area":null},{"id":"2310.07325","title":"An Adversarial Example for Direct Logit Attribution: Memory Management in GELU-4L","created":"2023-10-11","cited_by_count":11,"area":null},{"id":"2405.18432","title":"Unsupervised Model Tree Heritage Recovery","created":"2024-05-28","cited_by_count":11,"area":null},{"id":"2405.08553","title":"Improving Transformers with Dynamically Composable Multi-Head Attention","created":"2024-05-14","cited_by_count":10,"area":null},{"id":"2407.11540","title":"Not Another Imputation Method: A Transformer-based Model for Missing Values in Tabular Datasets","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2506.06231","title":"Towards an Explainable Comparison and Alignment of Feature Embeddings","created":"2025-06-06","cited_by_count":10,"area":null},{"id":"2506.08210","title":"A Comprehensive Study of Decoder-Only LLMs for Text-to-Image Generation","created":"2025-06-09","cited_by_count":10,"area":null},{"id":"2502.10927","title":"The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer training","created":"2025-02-15","cited_by_count":9,"area":null},{"id":"2505.16538","title":"Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models","created":"2025-05-22","cited_by_count":8,"area":null},{"id":"2510.24907","title":"Understanding Multi-View Transformers","created":"2025-10-28","cited_by_count":8,"area":null},{"id":"2309.07315","title":"Traveling Words: A Geometric Interpretation of Transformers","created":"2023-09-13","cited_by_count":7,"area":null},{"id":"2405.17653","title":"InversionView: A General-Purpose Method for Reading Information from Neural Activations","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2510.04933","title":"The Geometry of Truth: Layer-wise Semantic Dynamics for Hallucination Detection in Large Language Models","created":"2025-10-06","cited_by_count":7,"area":null},{"id":"2405.11891","title":"Unveiling and Manipulating Prompt Influence in Large Language Models","created":"2024-05-20","cited_by_count":6,"area":null},{"id":"2502.10871","title":"Layerwise Recall and the Geometry of Interwoven Knowledge in LLMs","created":"2025-02-15","cited_by_count":6,"area":null},{"id":"2406.13185","title":"LIVE: Learnable In-Context Vector for Visual Question Answering","created":"2024-06-19","cited_by_count":5,"area":null},{"id":"2407.06162","title":"RNNs, CNNs and Transformers in Human Action Recognition: A Survey and a Hybrid Model","created":"2024-06-02","cited_by_count":5,"area":null},{"id":"2504.15471","title":"Bigram Subnetworks: Mapping to Next Tokens in Transformer Language Models","created":"2025-04-21","cited_by_count":5,"area":null},{"id":"2512.16902","title":"In-Context Algebra","created":"2025-12-18","cited_by_count":5,"area":null},{"id":"2602.00398","title":"MemoryLLM: Plug-n-Play Interpretable Feed-Forward Memory for Transformers","created":"2026-01-30","cited_by_count":5,"area":null},{"id":"2411.17182","title":"An In-depth Investigation of Sparse Rate Reduction in Transformer-like Models","created":"2024-11-26","cited_by_count":4,"area":null},{"id":"2505.13515","title":"LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades","created":"2025-05-17","cited_by_count":4,"area":null},{"id":"2507.00322","title":"Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones","created":"2025-06-30","cited_by_count":4,"area":null},{"id":"2510.02348","title":"mini-vec2vec: Scaling Universal Geometry Alignment with Linear Transformations","created":"2025-09-27","cited_by_count":4,"area":null},{"id":"2510.02524","title":"Unraveling Syntax: Language Modeling and the Substructure of Grammars","created":"2025-10-02","cited_by_count":4,"area":null},{"id":"2606.03280","title":"A Negative Result on Cross-Model Activation Transfer in a Pythia Multi-Hop Setting","created":"2026-06-02","cited_by_count":4,"area":null},{"id":"2406.02721","title":"Self-Control of LLM Behaviors by Compressing Suffix Gradient into Prefix Controller","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2504.16871","title":"Exploring How LLMs Capture and Represent Domain-Specific Knowledge","created":"2025-04-23","cited_by_count":3,"area":null},{"id":"2510.21834","title":"Restoring Pruned Large Language Models via Lost Component Compensation","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2607.04319","title":"Legible-by-Construction: Attention and End-to-End Transformers","created":"2026-07-05","cited_by_count":3,"area":null},{"id":"2310.06977","title":"Why bother with geometry? On the relevance of linear decompositions of Transformer embeddings","created":"2023-10-10","cited_by_count":2,"area":null},{"id":"2406.02060","title":"I've got the \"Answer\"! Interpretation of LLMs Hidden States in Question Answering","created":"2024-06-04","cited_by_count":2,"area":null},{"id":"2502.11646","title":"Hyper-SET: Designing Transformers via Hyperspherical Energy Minimization","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2507.05387","title":"The Generalization Ridge: Information Flow in Natural Language Generation","created":"2025-07-07","cited_by_count":2,"area":null},{"id":"2509.20124","title":"Probability Signature: Bridging Data Semantics and Embedding Structure in Language Models","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2511.05852","title":"Can Fine-Tuning Erase Your Edits? On the Fragile Coexistence of Knowledge Editing and Adaptation","created":"2025-11-08","cited_by_count":2,"area":null},{"id":"2605.17084","title":"Scale Determines Whether Language Models Organize Representation Geometry for Prediction","created":"2026-05-16","cited_by_count":2,"area":null},{"id":"2409.19097","title":"Implementing NLPs in industrial process modeling: Addressing Categorical Variables","created":"2024-09-27","cited_by_count":1,"area":null},{"id":"2411.07071","title":"Universal Response and Emergence of Induction in LLMs","created":"2024-11-11","cited_by_count":1,"area":null},{"id":"2505.17260","title":"The Rise of Parameter Specialization for Knowledge Storage in Large Language Models","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2506.07658","title":"From Raw Corpora to Domain Benchmarks: Automated Evaluation of LLM Domain Expertise","created":"2025-06-09","cited_by_count":1,"area":null},{"id":"2601.01526","title":"BARE: Towards Bias-Aware and Reasoning-Enhanced One-Tower Visual Grounding","created":"2026-01-04","cited_by_count":1,"area":null},{"id":"2605.27970","title":"Geometry of Human Perceptual Domains Emerges Transiently in LLM Representations","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2607.08946","title":"Training, Reading, and Editing Legible Transformers","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2609.10210","title":"Through the Looking Glass: Directly Reading and Writing Transformers","created":"2026-09-09","cited_by_count":1,"area":null},{"id":"2408.17324","title":"Modularity in Transformers: Investigating Neuron Separability & Specialization","created":"2024-08-30","cited_by_count":0,"area":null},{"id":"2505.18244","title":"Emergent Hierarchical Structure in Large Language Models: An Information-Theoretic Framework for Multi-Scale Representation","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2512.05461","title":"Knowing Your Uncertainty -- On the application of LLM in social sciences","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2605.06216","title":"TIDE: Every Layer Knows the Token Beneath the Context","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.22202","title":"Structure Retention in Embedding Spaces as a Predictor of Benchmark Performance","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2605.31497","title":"Assign and Add: A Mechanistic Study of Compositional Arithmetic","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.20208","title":"surprisal is Not a Theory","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2607.26179","title":"Cognitive Convergence: Deep Similarities Between Large Language Models and Human Cognition","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.29279","title":"Understanding Deep Learning via Entropy Space Theory","created":"2026-08-29","cited_by_count":0,"area":null}],"next_cursor":null}