{"total":532,"rows":[{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001,"area":null},{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716,"area":null},{"id":"2303.08112","title":"Eliciting Latent Predictions from Transformers with the Tuned Lens","created":"2023-03-14","cited_by_count":623,"area":"mechinterp"},{"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":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2309.12288","title":"The Reversal Curse: LLMs trained on \"A is B\" fail to learn \"B is A\"","created":"2023-09-21","cited_by_count":407,"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":"2309.16042","title":"Towards Best Practices of Activation Patching in Language Models: Metrics and Methods","created":"2023-09-27","cited_by_count":359,"area":"mechinterp"},{"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":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2207.07061","title":"Confident Adaptive Language Modeling","created":"2022-07-14","cited_by_count":310,"area":"inference"},{"id":"2310.15213","title":"Function Vectors in Large Language Models","created":"2023-10-23","cited_by_count":308,"area":null},{"id":"2404.16710","title":"LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding","created":"2024-04-25","cited_by_count":307,"area":"inference"},{"id":"2402.10588","title":"Do Llamas Work in English? On the Latent Language of Multilingual Transformers","created":"2024-02-16","cited_by_count":281,"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":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2401.06102","title":"Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models","created":"2024-01-11","cited_by_count":235,"area":"mechinterp"},{"id":"2310.07521","title":"Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity","created":"2023-10-11","cited_by_count":206,"area":null},{"id":"2305.00586","title":"How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model","created":"2023-04-30","cited_by_count":202,"area":null},{"id":"2308.09124","title":"Linearity of Relation Decoding in Transformer Language Models","created":"2023-08-17","cited_by_count":200,"area":null},{"id":"2305.01644","title":"Key-Locked Rank One Editing for Text-to-Image Personalization","created":"2023-05-02","cited_by_count":194,"area":null},{"id":"2310.16218","title":"Knowledge Editing for Large Language Models: A Survey","created":"2023-10-24","cited_by_count":194,"area":"lr"},{"id":"2401.01967","title":"A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity","created":"2024-01-03","cited_by_count":185,"area":"alignment"},{"id":"2308.08742","title":"PMET: Precise Model Editing in a Transformer","created":"2023-08-17","cited_by_count":173,"area":null},{"id":"2402.16837","title":"Do Large Language Models Latently Perform Multi-Hop Reasoning?","created":"2024-02-26","cited_by_count":169,"area":"lr"},{"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":"2410.12877","title":"Improving Instruction-Following in Language Models through Activation Steering","created":"2024-10-15","cited_by_count":160,"area":"mechinterp"},{"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":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152,"area":"inference"},{"id":"2402.18815","title":"How do Large Language Models Handle Multilingualism?","created":"2024-02-29","cited_by_count":150,"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":"2411.16724","title":"Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens","created":"2024-11-23","cited_by_count":143,"area":"mllm"},{"id":"2209.02535","title":"Analyzing Transformers in Embedding Space","created":"2022-09-06","cited_by_count":132,"area":null},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2410.07149","title":"Towards Interpreting Visual Information Processing in Vision-Language Models","created":"2024-10-09","cited_by_count":122,"area":"mllm"},{"id":"2402.05602","title":"AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers","created":"2024-02-08","cited_by_count":120,"area":"lr"},{"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":"2311.12786","title":"Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks","created":"2023-11-21","cited_by_count":115,"area":null},{"id":"2401.17256","title":"Weak-to-Strong Jailbreaking on Large Language Models","created":"2024-01-30","cited_by_count":107,"area":"safety"},{"id":"2401.04700","title":"Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue","created":"2024-01-09","cited_by_count":103,"area":null},{"id":"2401.12181","title":"Universal Neurons in GPT2 Language Models","created":"2024-01-22","cited_by_count":102,"area":"mechinterp"},{"id":"2305.16130","title":"Language Models Implement Simple Word2Vec-style Vector Arithmetic","created":"2023-05-25","cited_by_count":98,"area":null},{"id":"2308.07269","title":"EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models","created":"2023-08-14","cited_by_count":98,"area":null},{"id":"2210.03329","title":"Calibrating Factual Knowledge in Pretrained Language Models","created":"2022-10-07","cited_by_count":92,"area":null},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2402.17811","title":"TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space","created":"2024-02-27","cited_by_count":91,"area":null},{"id":"2402.18154","title":"Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models","created":"2024-02-28","cited_by_count":91,"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":"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":"2309.04827","title":"Neurons in Large Language Models: Dead, N-gram, Positional","created":"2023-09-09","cited_by_count":88,"area":null},{"id":"2403.14472","title":"Detoxifying Large Language Models via Knowledge Editing","created":"2024-03-21","cited_by_count":87,"area":null},{"id":"2210.07700","title":"Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey","created":"2022-10-14","cited_by_count":80,"area":null},{"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":"2405.18166","title":"Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing","created":"2024-05-28","cited_by_count":79,"area":"safety"},{"id":"2406.12775","title":"Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop Queries","created":"2024-06-18","cited_by_count":78,"area":null},{"id":"2607.15495","title":"Verbalizable Representations Form a Global Workspace in Language Models","created":"2026-07-16","cited_by_count":75,"area":null},{"id":"2210.03588","title":"Understanding Transformer Memorization Recall Through Idioms","created":"2022-10-07","cited_by_count":62,"area":null},{"id":"2405.17969","title":"Knowledge Circuits in Pretrained Transformers","created":"2024-05-28","cited_by_count":60,"area":"mechinterp"},{"id":"2406.16254","title":"Confidence Regulation Neurons in Language Models","created":"2024-06-24","cited_by_count":57,"area":null},{"id":"2402.09221","title":"Spectral Filters, Dark Signals, and Attention Sinks","created":"2024-02-14","cited_by_count":56,"area":"mechinterp"},{"id":"2310.11877","title":"The Curious Case of Hallucinatory (Un)answerability: Finding Truths in the Hidden States of Over-Confident Large Language Models","created":"2023-10-18","cited_by_count":55,"area":null},{"id":"2408.16730","title":"VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation","created":"2024-08-29","cited_by_count":55,"area":"mllm"},{"id":"2409.01658","title":"From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning","created":"2024-09-03","cited_by_count":54,"area":null},{"id":"2402.09733","title":"Do LLMs Know about Hallucination? An Empirical Investigation of LLM's Hidden States","created":"2024-02-15","cited_by_count":52,"area":null},{"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":"2506.02867","title":"Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning","created":"2025-06-03","cited_by_count":51,"area":"lr"},{"id":"2408.11491","title":"SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering","created":"2024-08-21","cited_by_count":50,"area":"alignment"},{"id":"2310.17086","title":"Transformers Learn to Achieve Second-Order Convergence Rates for In-Context Linear Regression","created":"2023-10-26","cited_by_count":49,"area":"offlinerl"},{"id":"2407.20516","title":"Machine Unlearning in Generative AI: A Survey","created":"2024-07-30","cited_by_count":49,"area":"safety"},{"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":"2310.09573","title":"Self-Detoxifying Language Models via Toxification Reversal","created":"2023-10-14","cited_by_count":46,"area":"safety"},{"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":"2309.10312","title":"Rigorously Assessing Natural Language Explanations of Neurons","created":"2023-09-19","cited_by_count":45,"area":null},{"id":"2409.01659","title":"Interpreting and Improving Large Language Models in Arithmetic Calculation","created":"2024-09-03","cited_by_count":45,"area":null},{"id":"2211.11152","title":"You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model","created":"2022-11-21","cited_by_count":43,"area":"mllm"},{"id":"2305.12535","title":"Explaining How Transformers Use Context to Build Predictions","created":"2023-05-21","cited_by_count":43,"area":null},{"id":"2403.20009","title":"On Large Language Models' Hallucination with Regard to Known Facts","created":"2024-03-29","cited_by_count":43,"area":null},{"id":"2402.07321","title":"Summing Up the Facts: Additive Mechanisms Behind Factual Recall in LLMs","created":"2024-02-11","cited_by_count":42,"area":null},{"id":"2306.01128","title":"Learning Transformer Programs","created":"2023-06-01","cited_by_count":41,"area":"mechinterp"},{"id":"2501.08319","title":"Enhancing Automated Interpretability with Output-Centric Feature Descriptions","created":"2025-01-14","cited_by_count":41,"area":null},{"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":"2403.18167","title":"Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations","created":"2024-03-27","cited_by_count":38,"area":null},{"id":"2305.18390","title":"Emergent Modularity in Pre-trained Transformers","created":"2023-05-28","cited_by_count":37,"area":null},{"id":"2312.12141","title":"Neuron-Level Knowledge Attribution in Large Language Models","created":"2023-12-19","cited_by_count":37,"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":"2402.18909","title":"AKEW: Assessing Knowledge Editing in the Wild","created":"2024-02-29","cited_by_count":36,"area":null},{"id":"2406.14479","title":"Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity","created":"2024-06-20","cited_by_count":36,"area":null},{"id":"2503.21073","title":"Shared Global and Local Geometry of Language Model Embeddings","created":"2025-03-27","cited_by_count":36,"area":null},{"id":"2405.13967","title":"Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity","created":"2024-05-22","cited_by_count":35,"area":"alignment"},{"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":"2410.04962","title":"Activation Scaling for Steering and Interpreting Language Models","created":"2024-10-07","cited_by_count":35,"area":null},{"id":"2306.00966","title":"The Hidden Language of Diffusion Models","created":"2023-06-01","cited_by_count":34,"area":"diffusion"},{"id":"2406.11194","title":"In-Context Editing: Learning Knowledge from Self-Induced Distributions","created":"2024-06-17","cited_by_count":34,"area":null},{"id":"2502.17516","title":"A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models","created":"2025-02-22","cited_by_count":34,"area":"mllm"},{"id":"2504.04635","title":"Steering off Course: Reliability Challenges in Steering Language Models","created":"2025-04-06","cited_by_count":34,"area":null},{"id":"2210.04492","title":"Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization","created":"2022-10-10","cited_by_count":33,"area":null},{"id":"2308.08090","title":"Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation","created":"2023-08-16","cited_by_count":33,"area":"safety"},{"id":"2406.09265","title":"Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMs","created":"2024-06-13","cited_by_count":33,"area":null}],"next_cursor":"100"}