{"total":225,"rows":[{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302,"area":null},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120,"area":null},{"id":"2312.06681","title":"Steering Llama 2 via Contrastive Activation Addition","created":"2023-12-09","cited_by_count":1085,"area":"mechinterp"},{"id":"2308.10248","title":"Steering Language Models With Activation Engineering","created":"2023-08-20","cited_by_count":922,"area":"mechinterp"},{"id":"2309.00941","title":"Emergent Linear Representations in World Models of Self-Supervised Sequence Models","created":"2023-09-02","cited_by_count":319,"area":"wm"},{"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":"2501.17148","title":"AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders","created":"2025-01-28","cited_by_count":218,"area":"mechinterp"},{"id":"2301.04709","title":"Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability","created":"2023-01-11","cited_by_count":205,"area":"mechinterp"},{"id":"2404.03592","title":"ReFT: Representation Finetuning for Language Models","created":"2024-04-04","cited_by_count":197,"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":"2507.03724","title":"MemOS: A Memory OS for AI System","created":"2025-07-04","cited_by_count":138,"area":"rag"},{"id":"2405.16833","title":"Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models","created":"2024-05-27","cited_by_count":125,"area":null},{"id":"2406.00045","title":"Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization","created":"2024-05-28","cited_by_count":118,"area":"alignment"},{"id":"2402.02416","title":"Aligner: Efficient Alignment by Learning to Correct","created":"2024-02-04","cited_by_count":98,"area":"alignment"},{"id":"2410.21272","title":"Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics","created":"2024-10-28","cited_by_count":97,"area":"lr"},{"id":"2411.11296","title":"Steering Language Model Refusal with Sparse Autoencoders","created":"2024-11-18","cited_by_count":95,"area":"mechinterp"},{"id":"2502.15603","title":"Do Multilingual LLMs Think In English?","created":"2025-02-21","cited_by_count":78,"area":"lr"},{"id":"2312.09230","title":"Successor Heads: Recurring, Interpretable Attention Heads In The Wild","created":"2023-12-14","cited_by_count":77,"area":null},{"id":"2406.00034","title":"Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories","created":"2024-05-26","cited_by_count":77,"area":"mechinterp"},{"id":"2404.01650","title":"Test-Time Model Adaptation with Only Forward Passes","created":"2024-04-02","cited_by_count":74,"area":null},{"id":"2505.22101","title":"MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Models","created":"2025-05-28","cited_by_count":73,"area":null},{"id":"2506.18167","title":"Understanding Reasoning in Thinking Language Models via Steering Vectors","created":"2025-06-22","cited_by_count":72,"area":"lr"},{"id":"2411.04986","title":"The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities","created":"2024-11-07","cited_by_count":69,"area":null},{"id":"2406.05954","title":"Aligning Large Language Models with Representation Editing: A Control Perspective","created":"2024-06-10","cited_by_count":64,"area":"alignment"},{"id":"2410.12299","title":"Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors","created":"2024-10-16","cited_by_count":63,"area":"mechinterp"},{"id":"2403.15498","title":"Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models","created":"2024-03-21","cited_by_count":62,"area":"wm"},{"id":"2405.09719","title":"Spectral Editing of Activations for Large Language Model Alignment","created":"2024-05-15","cited_by_count":56,"area":"alignment"},{"id":"2402.09631","title":"Representation Surgery: Theory and Practice of Affine Steering","created":"2024-02-15","cited_by_count":50,"area":null},{"id":"2505.22637","title":"Understanding (Un)Reliability of Steering Vectors in Language Models","created":"2025-05-28","cited_by_count":47,"area":"mechinterp"},{"id":"2406.15518","title":"Steering Without Side Effects: Improving Post-Deployment Control of Language Models","created":"2024-06-21","cited_by_count":46,"area":"safety"},{"id":"2502.02716","title":"A Unified Understanding and Evaluation of Steering Methods","created":"2025-02-04","cited_by_count":46,"area":"mechinterp"},{"id":"2507.16003","title":"Learning without training: The implicit dynamics of in-context learning","created":"2025-07-21","cited_by_count":43,"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":"2505.20977","title":"Evaluating and Steering Modality Preferences in Multimodal Large Language Model","created":"2025-05-27","cited_by_count":33,"area":"mllm"},{"id":"2505.22411","title":"Mitigating Overthinking in Large Reasoning Models via Manifold Steering","created":"2025-05-28","cited_by_count":33,"area":"lr"},{"id":"2410.22685","title":"Improving Uncertainty Quantification in Large Language Models via Semantic Embeddings","created":"2024-10-30","cited_by_count":30,"area":null},{"id":"2402.09236","title":"Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Models","created":"2024-02-14","cited_by_count":29,"area":null},{"id":"2406.00244","title":"Controlling Large Language Model Agents with Entropic Activation Steering","created":"2024-06-01","cited_by_count":29,"area":"agents"},{"id":"2502.18862","title":"One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs","created":"2025-02-26","cited_by_count":29,"area":"mechinterp"},{"id":"2410.14516","title":"Do LLMs \"know\" internally when they follow instructions?","created":"2024-10-18","cited_by_count":26,"area":null},{"id":"2605.05115","title":"Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior","created":"2026-05-06","cited_by_count":26,"area":null},{"id":"2410.09047","title":"Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models","created":"2024-10-11","cited_by_count":23,"area":"mllm"},{"id":"2504.12459","title":"On Linear Representations and Pretraining Data Frequency in Language Models","created":"2025-04-16","cited_by_count":23,"area":null},{"id":"2310.08043","title":"Understanding and Controlling a Maze-Solving Policy Network","created":"2023-10-12","cited_by_count":22,"area":null},{"id":"2505.14827","title":"Text Generation Beyond Discrete Token Sampling","created":"2025-05-20","cited_by_count":21,"area":null},{"id":"2505.20809","title":"Improved Representation Steering for Language Models","created":"2025-05-27","cited_by_count":21,"area":"mechinterp"},{"id":"2405.15454","title":"LiSeCo: Linear Semantic Control for Language Generation","created":"2024-05-24","cited_by_count":20,"area":null},{"id":"2511.05408","title":"Steering Language Models with Weight Arithmetic","created":"2025-11-07","cited_by_count":20,"area":null},{"id":"2404.09971","title":"Constructing Benchmarks and Interventions for Combating Hallucinations in LLMs","created":"2024-04-15","cited_by_count":19,"area":null},{"id":"2406.04331","title":"PaCE: Parsimonious Concept Engineering for Large Language Models","created":"2024-06-06","cited_by_count":19,"area":null},{"id":"2409.04185","title":"Residual Stream Analysis with Multi-Layer SAEs","created":"2024-09-06","cited_by_count":19,"area":"mechinterp"},{"id":"2405.04160","title":"A Causal Explainable Guardrails for Large Language Models","created":"2024-05-07","cited_by_count":18,"area":"safety"},{"id":"2505.12189","title":"Mitigating Content Effects on Reasoning in Language Models through Fine-Grained Activation Steering","created":"2025-05-18","cited_by_count":18,"area":"lr"},{"id":"2510.22042","title":"Emotions Where Art Thou: Understanding and Characterizing the Emotional Latent Space of Large Language Models","created":"2025-10-24","cited_by_count":18,"area":null},{"id":"2503.22048","title":"ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models","created":"2025-03-27","cited_by_count":17,"area":"lr"},{"id":"2501.03012","title":"Analyzing Finetuning Representation Shift for Multimodal LLMs Steering","created":"2025-01-06","cited_by_count":16,"area":"mllm"},{"id":"2501.14082","title":"Communicating Activations Between Language Model Agents","created":"2025-01-23","cited_by_count":16,"area":"lr"},{"id":"2502.00919","title":"Attention Sinks: A 'Catch, Tag, Release' Mechanism for Embeddings","created":"2025-02-02","cited_by_count":16,"area":null},{"id":"2406.03631","title":"Discovering Bias in Latent Space: An Unsupervised Debiasing Approach","created":"2024-06-05","cited_by_count":15,"area":null},{"id":"2511.22697","title":"Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations","created":"2025-11-27","cited_by_count":15,"area":"mllm"},{"id":"2602.02315","title":"The Shape of Beliefs: Geometry, Dynamics, and Interventions along Representation Manifolds of Language Models' Posteriors","created":"2026-02-02","cited_by_count":15,"area":null},{"id":"2409.14026","title":"Uncovering Latent Chain of Thought Vectors in Language Models","created":"2024-09-21","cited_by_count":14,"area":"lr"},{"id":"2412.10427","title":"Identifying and Manipulating Personality Traits in LLMs Through Activation Engineering","created":"2024-12-10","cited_by_count":14,"area":null},{"id":"2302.12480","title":"Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?","created":"2023-02-24","cited_by_count":13,"area":null},{"id":"2406.11978","title":"Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner","created":"2024-06-17","cited_by_count":13,"area":"agents"},{"id":"2508.12535","title":"CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder Features","created":"2025-08-18","cited_by_count":12,"area":"mechinterp"},{"id":"2602.15669","title":"PERSONA: Dynamic and Compositional Inference-Time Personality Control via Activation Vector Algebra","created":"2026-02-17","cited_by_count":12,"area":null},{"id":"2405.14660","title":"Implicit In-context Learning","created":"2024-05-23","cited_by_count":11,"area":null},{"id":"2410.02899","title":"FactCheckmate: Preemptively Detecting and Mitigating Hallucinations in LMs","created":"2024-10-03","cited_by_count":11,"area":null},{"id":"2502.05390","title":"Learning Task Representations from In-Context Learning","created":"2025-02-08","cited_by_count":11,"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":"2410.21471","title":"AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion models","created":"2024-10-28","cited_by_count":10,"area":"diffusion"},{"id":"2506.19382","title":"Measuring and Guiding Monosemanticity","created":"2025-06-24","cited_by_count":10,"area":"mechinterp"},{"id":"2507.08218","title":"Simple Mechanistic Explanations for Out-Of-Context Reasoning","created":"2025-07-10","cited_by_count":10,"area":"lr"},{"id":"2508.11277","title":"Probing the Representational Power of Sparse Autoencoders in Vision Models","created":"2025-08-15","cited_by_count":10,"area":"diffusion"},{"id":"2510.04491","title":"Impatient Users Confuse AI Agents: High-fidelity Simulations of Human Traits for Testing Agents","created":"2025-10-06","cited_by_count":10,"area":null},{"id":"2605.01148","title":"Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts","created":"2026-05-01","cited_by_count":10,"area":null},{"id":"2406.11624","title":"Words in Motion: Extracting Interpretable Control Vectors for Motion Transformers","created":"2024-06-17","cited_by_count":9,"area":null},{"id":"2409.06328","title":"Extracting Paragraphs from LLM Token Activations","created":"2024-09-10","cited_by_count":9,"area":null},{"id":"2512.24143","title":"Activation Steering for Masked Diffusion Language Models","created":"2025-12-30","cited_by_count":9,"area":"diffusion"},{"id":"2404.05783","title":"A Survey on Responsible Generative AI: What to Generate and What Not","created":"2024-04-08","cited_by_count":8,"area":null},{"id":"2410.22888","title":"Effective and Efficient Adversarial Detection for Vision-Language Models via A Single Vector","created":"2024-10-30","cited_by_count":8,"area":"mllm"},{"id":"2504.20500","title":"UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation","created":"2025-04-29","cited_by_count":8,"area":null},{"id":"2507.06445","title":"Can Interpretation Predict Behavior on Unseen Data?","created":"2025-07-08","cited_by_count":8,"area":null},{"id":"2602.00333","title":"Efficient and accurate steering of Large Language Models through attention-guided feature learning","created":"2026-01-30","cited_by_count":8,"area":null},{"id":"2603.01281","title":"Spectral Attention Steering for Prompt Highlighting","created":"2026-03-01","cited_by_count":8,"area":null},{"id":"2604.09839","title":"Steered LLM Activations are Non-Surjective","created":"2026-04-10","cited_by_count":8,"area":"mechinterp"},{"id":"2305.19512","title":"Fine-grained Text Style Transfer with Diffusion-Based Language Models","created":"2023-05-31","cited_by_count":7,"area":"diffusion"},{"id":"2503.02989","title":"Effectively Steer LLM To Follow Preference via Building Confident Directions","created":"2025-03-04","cited_by_count":7,"area":"alignment"},{"id":"2505.23816","title":"A Course Correction in Steerability Evaluation: Revealing Miscalibration and Side Effects in LLMs","created":"2025-05-27","cited_by_count":7,"area":"lr"},{"id":"2509.07983","title":"Steering Protein Language Models","created":"2025-07-01","cited_by_count":7,"area":null},{"id":"2512.15134","title":"From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?","created":"2025-12-17","cited_by_count":7,"area":null},{"id":"2602.05859","title":"DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders","created":"2026-02-05","cited_by_count":7,"area":"diffusion"},{"id":"2502.04075","title":"From Rational Answers to Emotional Resonance: The Role of Controllable Emotion Generation in Language Models","created":"2025-02-06","cited_by_count":6,"area":null},{"id":"2504.20106","title":"Adaptive Helpfulness-Harmlessness Alignment with Preference Vectors","created":"2025-04-27","cited_by_count":6,"area":"alignment"},{"id":"2507.01368","title":"Activation Reward Models for Few-Shot Model Alignment","created":"2025-07-02","cited_by_count":6,"area":"mllm"},{"id":"2602.10161","title":"Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignment","created":"2026-02-10","cited_by_count":6,"area":null},{"id":"2410.22944","title":"Focus On This, Not That! Steering LLMs with Adaptive Feature Specification","created":"2024-10-30","cited_by_count":5,"area":null},{"id":"2502.06809","title":"Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution","created":"2025-02-04","cited_by_count":5,"area":null},{"id":"2504.00194","title":"Identifying Sparsely Active Circuits Through Local Loss Landscape Decomposition","created":"2025-03-31","cited_by_count":5,"area":"mechinterp"}],"next_cursor":"100"}