{"total":121,"rows":[{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2404.19737","title":"Better & Faster Large Language Models via Multi-token Prediction","created":"2024-04-30","cited_by_count":360,"area":null},{"id":"2406.15927","title":"Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs","created":"2024-06-22","cited_by_count":259,"area":null},{"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":"2404.15758","title":"Let's Think Dot by Dot: Hidden Computation in Transformer Language Models","created":"2024-04-24","cited_by_count":191,"area":"lr"},{"id":"2403.06963","title":"The pitfalls of next-token prediction","created":"2024-03-11","cited_by_count":160,"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":"2507.11878","title":"LLMs Encode Harmfulness and Refusal Separately","created":"2025-07-16","cited_by_count":88,"area":"safety"},{"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":"2502.15603","title":"Do Multilingual LLMs Think In English?","created":"2025-02-21","cited_by_count":78,"area":"lr"},{"id":"2405.15943","title":"Transformers represent belief state geometry in their residual stream","created":"2024-05-24","cited_by_count":77,"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":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"area":null},{"id":"2412.08686","title":"LatentQA: Teaching LLMs to Decode Activations Into Natural Language","created":"2024-12-11","cited_by_count":51,"area":null},{"id":"2404.00859","title":"Do language models plan ahead for future tokens?","created":"2024-04-01","cited_by_count":49,"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":"2406.12094","title":"Who's asking? User personas and the mechanics of latent misalignment","created":"2024-06-17","cited_by_count":40,"area":"safety"},{"id":"2402.11131","title":"Speculative Streaming: Fast LLM Inference without Auxiliary Models","created":"2024-02-16","cited_by_count":38,"area":"inference"},{"id":"2312.12141","title":"Neuron-Level Knowledge Attribution in Large Language Models","created":"2023-12-19","cited_by_count":37,"area":null},{"id":"2509.21305","title":"Sycophancy Is Not One Thing: Causal Separation of Sycophantic Behaviors in LLMs","created":"2025-09-25","cited_by_count":37,"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":"2409.14381","title":"Investigating Layer Importance in Large Language Models","created":"2024-09-22","cited_by_count":36,"area":null},{"id":"2406.00877","title":"Evidence of Learned Look-Ahead in a Chess-Playing Neural Network","created":"2024-06-02","cited_by_count":34,"area":null},{"id":"2505.17127","title":"Pixels Versus Priors: Controlling Knowledge Priors in Vision-Language Models through Visual Counterfacts","created":"2025-05-21","cited_by_count":32,"area":"mllm"},{"id":"2403.19851","title":"Localizing Paragraph Memorization in Language Models","created":"2024-03-28","cited_by_count":31,"area":null},{"id":"2403.05846","title":"Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines","created":"2024-03-09","cited_by_count":30,"area":"diffusion"},{"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":"2506.17871","title":"LLM Probability Concentration: How Alignment Shrinks the Generative Horizon","created":"2025-06-22","cited_by_count":26,"area":"alignment"},{"id":"2407.19200","title":"On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs","created":"2024-07-27","cited_by_count":25,"area":"mechinterp"},{"id":"2412.10321","title":"AdvPrefix: An Objective for Nuanced LLM Jailbreaks","created":"2024-12-13","cited_by_count":25,"area":"safety"},{"id":"2504.03022","title":"The Dual-Route Model of Induction","created":"2025-04-03","cited_by_count":24,"area":null},{"id":"2406.16033","title":"Unlocking the Future: Exploring Look-Ahead Planning Mechanistic Interpretability in Large Language Models","created":"2024-06-23","cited_by_count":22,"area":"mechinterp"},{"id":"2407.02446","title":"Predicting vs. Acting: A Trade-off Between World Modeling & Agent Modeling","created":"2024-07-02","cited_by_count":20,"area":"wm"},{"id":"2502.06258","title":"Emergent Response Planning in LLMs","created":"2025-02-10","cited_by_count":19,"area":"lr"},{"id":"2406.14511","title":"Investigating Mysteries of CoT-Augmented Distillation","created":"2024-06-20","cited_by_count":16,"area":"lr"},{"id":"2510.18871","title":"How Do LLMs Use Their Depth?","created":"2025-10-21","cited_by_count":16,"area":null},{"id":"2405.14992","title":"Linking In-context Learning in Transformers to Human Episodic Memory","created":"2024-05-23","cited_by_count":15,"area":null},{"id":"2503.19693","title":"AdaptiVocab: Enhancing LLM Efficiency in Focused Domains through Lightweight Vocabulary Adaptation","created":"2025-03-25","cited_by_count":15,"area":null},{"id":"2410.23501","title":"All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling","created":"2024-10-30","cited_by_count":14,"area":null},{"id":"2412.11867","title":"Transformers Use Causal World Models in Maze-Solving Tasks","created":"2024-12-16","cited_by_count":13,"area":"wm"},{"id":"2504.01928","title":"Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure","created":"2025-04-02","cited_by_count":13,"area":null},{"id":"2510.04013","title":"LLM Microscope: What Model Internals Reveal About Answer Correctness and Context Utilization","created":"2025-10-05","cited_by_count":11,"area":null},{"id":"2506.05451","title":"Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety","created":"2025-06-05","cited_by_count":10,"area":"safety"},{"id":"2404.05971","title":"Does Transformer Interpretability Transfer to RNNs?","created":"2024-04-09","cited_by_count":9,"area":"ssm"},{"id":"2409.06328","title":"Extracting Paragraphs from LLM Token Activations","created":"2024-09-10","cited_by_count":9,"area":null},{"id":"2502.13329","title":"Language Models Can Predict Their Own Behavior","created":"2025-02-18","cited_by_count":8,"area":"lr"},{"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":"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":"2511.19265","title":"Unboxing the Black Box: Mechanistic Interpretability for Algorithmic Understanding of Neural Networks","created":"2025-11-24","cited_by_count":6,"area":"mechinterp"},{"id":"2603.02913","title":"Eliciting Numerical Predictive Distributions of LLMs Without Autoregression","created":"2026-03-03","cited_by_count":6,"area":null},{"id":"2604.12493","title":"Latent Planning Emerges with Scale","created":"2026-04-14","cited_by_count":6,"area":null},{"id":"2605.25459","title":"From Simulation to Enaction: Post-trained language models recognize and react to their own generations","created":"2026-05-25","cited_by_count":6,"area":null},{"id":"2404.07066","title":"Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers?","created":"2024-04-10","cited_by_count":4,"area":null},{"id":"2410.00451","title":"Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models","created":"2024-10-01","cited_by_count":4,"area":"alignment"},{"id":"2410.11660","title":"Eliciting Textual Descriptions from Representations of Continuous Prompts","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2506.10138","title":"Path Channels and Plan Extension Kernels: a Mechanistic Description of Planning in a Sokoban RNN","created":"2025-06-11","cited_by_count":4,"area":"deeprl"},{"id":"2605.24956","title":"NITP: Next Implicit Token Prediction for LLM Pre-training","created":"2026-05-24","cited_by_count":4,"area":"moe"},{"id":"2503.10542","title":"Language Models, Graph Searching, and Supervision Adulteration: When More Supervision is Less and How to Make More More","created":"2025-03-13","cited_by_count":3,"area":null},{"id":"2504.18048","title":"Modes of Sequence Models and Learning Coefficients","created":"2025-04-25","cited_by_count":3,"area":null},{"id":"2510.14453","title":"Natural Language Tools: A Natural Language Approach to Tool Calling In Large Language Agents","created":"2025-10-16","cited_by_count":3,"area":"agents"},{"id":"2605.09969","title":"The Truth Lies Somewhere in the Middle (of the Generated Tokens)","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2607.01218","title":"The State-Prediction Separation Hypothesis","created":"2026-07-01","cited_by_count":3,"area":null},{"id":"2607.06763","title":"Trees from Marginals: Autoregressive drafting with factorized priors","created":"2026-07-07","cited_by_count":3,"area":"inference"},{"id":"2501.06382","title":"Dynamics of Spontaneous Topic Changes in Next Token Prediction with Self-Attention","created":"2025-01-10","cited_by_count":2,"area":null},{"id":"2505.22757","title":"Pre-Training Curriculum for Multi-Token Prediction in Language Models","created":"2025-05-28","cited_by_count":2,"area":"inference"},{"id":"2508.18098","title":"Detecting and Characterizing Planning in Language Models","created":"2025-08-25","cited_by_count":2,"area":null},{"id":"2509.23204","title":"Steering Prepositional Phrases in Language Models: A Case of with-headed Adjectival and Adverbial Complements in Gemma-2","created":"2025-09-27","cited_by_count":2,"area":null},{"id":"2510.13161","title":"Mirror Speculative Decoding: Breaking the Serial Barrier in LLM Inference","created":"2025-10-15","cited_by_count":2,"area":"inference"},{"id":"2511.00180","title":"ParaScopes: What do Language Models Activations Encode About Future Text?","created":"2025-10-31","cited_by_count":2,"area":null},{"id":"2602.02103","title":"How Far Ahead Do LLMs Plan? Uncovering the Latent Horizon in Chain-of-Thought Reasoning","created":"2026-02-02","cited_by_count":2,"area":"lr"},{"id":"2604.01202","title":"Therefore I am. I Think","created":"2026-04-01","cited_by_count":2,"area":"lr"},{"id":"2607.03502","title":"Reading Between the Dots: Decoding Hidden Computation across Filler Tokens","created":"2026-07-03","cited_by_count":2,"area":"lr"},{"id":"2402.13113","title":"When Only Time Will Tell: Interpreting How Transformers Process Local Ambiguities Through the Lens of Restart-Incrementality","created":"2024-02-20","cited_by_count":1,"area":null},{"id":"2407.11421","title":"States Hidden in Hidden States: Implicit Discrete State Representations Emerge in LLMs' Hidden States","created":"2024-07-16","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":"2505.11576","title":"Concept-Guided Interpretability via Neural Chunking","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2508.15875","title":"NEAT: Concept driven Neuron Attribution in LLMs","created":"2025-08-21","cited_by_count":1,"area":null},{"id":"2509.24435","title":"Alternatives To Next Token Prediction In Text Generation -- A Survey","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2509.25260","title":"Internal Planning in Language Models: Characterizing Horizon and Branch Awareness","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2510.09421","title":"On the Representations of Entities in Auto-regressive Large Language Models","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2512.00725","title":"ESMC: MLLM-Based Embedding Selection for Explainable Multiple Clustering","created":"2025-11-30","cited_by_count":1,"area":null},{"id":"2601.02569","title":"LoRA-Drop: Temporal LoRA Decoding for Efficient LLM Inference","created":"2026-01-05","cited_by_count":1,"area":"inference"},{"id":"2602.08964","title":"A Behavioural and Representational Evaluation of Goal-Directedness in Language Model Agents","created":"2026-02-09","cited_by_count":1,"area":"agents"},{"id":"2607.05188","title":"Latent Programming Horizons in Coding Agents","created":"2026-07-06","cited_by_count":1,"area":"agents"},{"id":"2607.08946","title":"Training, Reading, and Editing Legible Transformers","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2609.02737","title":"Language Models Can Control Their Own Attention","created":"2026-09-02","cited_by_count":1,"area":"inference"},{"id":"2409.09568","title":"Thesis proposal: Are We Losing Textual Diversity to Natural Language Processing?","created":"2024-09-15","cited_by_count":0,"area":null},{"id":"2410.18160","title":"Future Token Prediction -- Causal Language Modelling with Per-Token Semantic State Vector for Multi-Token Prediction","created":"2024-10-23","cited_by_count":0,"area":null},{"id":"2502.01803","title":"Discovering Chunks in Neural Embeddings for Interpretability","created":"2025-02-03","cited_by_count":0,"area":null},{"id":"2505.21552","title":"Understanding the learned look-ahead behavior of chess neural networks","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2507.02241","title":"VERBA: Verbalizing Model Differences Using Large Language Models","created":"2025-07-03","cited_by_count":0,"area":null},{"id":"2507.13858","title":"InTraVisTo: Inside Transformer Visualisation Tool","created":"2025-07-18","cited_by_count":0,"area":"lr"},{"id":"2507.17618","title":"SimLens for Early Exit in Large Language Models: Eliciting Accurate Latent Predictions with One More Token","created":"2025-07-23","cited_by_count":0,"area":"inference"},{"id":"2511.18359","title":"TRANSPORTER: Transferring Visual Semantics from VLM Manifolds","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2512.23837","title":"Adversarial Lens: Exploiting Attention Layers to Generate Adversarial Examples for Evaluation","created":"2025-12-29","cited_by_count":0,"area":"mechinterp"},{"id":"2602.01897","title":"Internal Flow Signatures for Self-Checking and Refinement in LLMs","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.02991","title":"Large Language Models Can Take False First Steps at Inference-time Planning","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2603.14087","title":"Understanding the Emergence of Seemingly Useless Features in Next-Token Predictors","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2603.17566","title":"KA2L: A Knowledge-Aware Active Learning Framework for LLMs","created":"2026-03-18","cited_by_count":0,"area":null}],"next_cursor":"100"}