{"total":393,"rows":[{"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":"2311.06668","title":"In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering","created":"2023-11-11","cited_by_count":245,"area":null},{"id":"2404.03592","title":"ReFT: Representation Finetuning for Language Models","created":"2024-04-04","cited_by_count":197,"area":null},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"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":"2506.19823","title":"Persona Features Control Emergent Misalignment","created":"2025-06-24","cited_by_count":86,"area":null},{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"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":"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":"2506.11618","title":"Convergent Linear Representations of Emergent Misalignment","created":"2025-06-13","cited_by_count":71,"area":null},{"id":"2604.07729","title":"Emotion Concepts and their Function in a Large Language Model","created":"2026-04-09","cited_by_count":57,"area":null},{"id":"2402.01618","title":"Style Vectors for Steering Generative Large Language Model","created":"2024-02-02","cited_by_count":56,"area":null},{"id":"2510.26243","title":"Angular Steering: Behavior Control via Rotation in Activation Space","created":"2025-10-30","cited_by_count":53,"area":null},{"id":"2512.15674","title":"Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers","created":"2025-12-17","cited_by_count":52,"area":null},{"id":"2311.08147","title":"RECALL: A Benchmark for LLMs Robustness against External Counterfactual Knowledge","created":"2023-11-14","cited_by_count":51,"area":null},{"id":"2310.17230","title":"Codebook Features: Sparse and Discrete Interpretability for Neural Networks","created":"2023-10-26","cited_by_count":48,"area":null},{"id":"2406.07882","title":"Designing a Dashboard for Transparency and Control of Conversational AI","created":"2024-06-12","cited_by_count":46,"area":null},{"id":"2502.12446","title":"Multi-Attribute Steering of Language Models via Targeted Intervention","created":"2025-02-18","cited_by_count":46,"area":null},{"id":"2505.13763","title":"Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations","created":"2025-05-19","cited_by_count":41,"area":null},{"id":"2402.15179","title":"Advancing Parameter Efficiency in Fine-tuning via Representation Editing","created":"2024-02-23","cited_by_count":37,"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":"2507.01786","title":"Probing and Steering Evaluation Awareness of Language Models","created":"2025-07-02","cited_by_count":35,"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":"2603.17839","title":"How do LLMs Compute Verbal Confidence","created":"2026-03-18","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":"2601.16644","title":"Sycophancy Hides Linearly in the Attention Heads","created":"2026-01-23","cited_by_count":23,"area":null},{"id":"2602.07852","title":"Emergent Misalignment is Easy, Narrow Misalignment is Hard","created":"2026-02-08","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":"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":"2409.02877","title":"Configurable Foundation Models: Building LLMs from a Modular Perspective","created":"2024-09-04","cited_by_count":22,"area":null},{"id":"2505.13141","title":"Language-Specific Latent Process Hinders Cross-Lingual Performance","created":"2025-05-19","cited_by_count":21,"area":null},{"id":"2505.14827","title":"Text Generation Beyond Discrete Token Sampling","created":"2025-05-20","cited_by_count":21,"area":null},{"id":"2505.20546","title":"Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline","created":"2025-05-26","cited_by_count":21,"area":null},{"id":"2511.05408","title":"Steering Language Models with Weight Arithmetic","created":"2025-11-07","cited_by_count":20,"area":null},{"id":"2506.00085","title":"COSMIC: Generalized Refusal Direction Identification in LLM Activations","created":"2025-05-30","cited_by_count":19,"area":null},{"id":"2402.19465","title":"Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models","created":"2024-02-29","cited_by_count":18,"area":null},{"id":"2506.10922","title":"Robustly Improving LLM Fairness in Realistic Settings via Interpretability","created":"2025-06-12","cited_by_count":18,"area":null},{"id":"2510.11288","title":"Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs","created":"2025-10-13","cited_by_count":17,"area":null},{"id":"2510.11328","title":"Do LLMs \"Feel\"? Emotion Circuits Discovery and Control","created":"2025-10-13","cited_by_count":17,"area":null},{"id":"2405.17345","title":"Exploring and steering the moral compass of Large Language Models","created":"2024-05-27","cited_by_count":16,"area":null},{"id":"2502.00919","title":"Attention Sinks: A 'Catch, Tag, Release' Mechanism for Embeddings","created":"2025-02-02","cited_by_count":16,"area":null},{"id":"2604.03147","title":"Valence-Arousal Subspace in LLMs: Circular Emotion Geometry and Multi-Behavioral Control","created":"2026-04-03","cited_by_count":16,"area":null},{"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":"2602.20031","title":"Latent Introspection: Models Can Detect Prior Concept Injections","created":"2026-02-23","cited_by_count":14,"area":null},{"id":"2501.08145","title":"Refusal Behavior in Large Language Models: A Nonlinear Perspective","created":"2025-01-14","cited_by_count":13,"area":null},{"id":"2509.25175","title":"EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering","created":"2025-09-29","cited_by_count":13,"area":null},{"id":"2511.22662","title":"Difficulties with Evaluating a Deception Detector for AIs","created":"2025-11-27","cited_by_count":13,"area":null},{"id":"2509.13281","title":"RepIt: Steering Language Models with Concept-Specific Refusal Vectors","created":"2025-09-16","cited_by_count":12,"area":null},{"id":"2601.08331","title":"CLaS-Bench: A Cross-Lingual Alignment and Steering Benchmark","created":"2026-01-13","cited_by_count":12,"area":null},{"id":"2602.02464","title":"From Directions to Regions: Decomposing Activations in Language Models via Local Geometry","created":"2026-02-02","cited_by_count":12,"area":null},{"id":"2602.11246","title":"How Many Features Can a Language Model Store Under the Linear Representation Hypothesis?","created":"2026-02-11","cited_by_count":12,"area":null},{"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":"2602.18899","title":"[b] = [d] - [t] + [p]: Self-supervised Speech Models Discover Phonological Vector Arithmetic","created":"2026-02-21","cited_by_count":12,"area":null},{"id":"2502.15639","title":"Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models","created":"2025-02-21","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":"2510.10157","title":"BILLY: Steering Large Language Models via Merging Persona Vectors for Creative Generation","created":"2025-10-11","cited_by_count":11,"area":null},{"id":"2602.15293","title":"The Information Geometry of Softmax: Probing and Steering","created":"2026-02-17","cited_by_count":11,"area":null},{"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":"2603.22161","title":"Causal Evidence that Language Models use Confidence to Drive Behavior","created":"2026-03-23","cited_by_count":10,"area":null},{"id":"2404.10464","title":"DESTEIN: Navigating Detoxification of Language Models via Universal Steering Pairs and Head-wise Activation Fusion","created":"2024-04-16","cited_by_count":9,"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":"2603.11863","title":"CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges","created":"2026-03-12","cited_by_count":9,"area":null},{"id":"2402.10453","title":"Steering Conversational Large Language Models for Long Emotional Support Conversations","created":"2024-02-16","cited_by_count":8,"area":null},{"id":"2405.13578","title":"ConTrans: Weak-to-Strong Alignment Engineering via Concept Transplantation","created":"2024-05-22","cited_by_count":8,"area":null},{"id":"2502.06470","title":"A Survey of Theory of Mind in Large Language Models: Evaluations, Representations, and Safety Risks","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2507.23220","title":"Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders","created":"2025-07-31","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":"2602.04735","title":"From Data to Behavior: Predicting Unintended Model Behaviors Before Training","created":"2026-02-04","cited_by_count":8,"area":null},{"id":"2602.20273","title":"The Truthfulness Spectrum Hypothesis","created":"2026-02-23","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":"2604.14090","title":"From Weights to Activations: Is Steering the Next Frontier of Adaptation?","created":"2026-04-15","cited_by_count":8,"area":null},{"id":"2606.29490","title":"Reported Confidence in LLMs Tracks Commitment More Than Correctness","created":"2026-06-28","cited_by_count":8,"area":null},{"id":"2506.00653","title":"Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models","created":"2025-05-31","cited_by_count":7,"area":null},{"id":"2507.21141","title":"The Geometry of Harmfulness in LLMs through Subconcept Probing","created":"2025-07-23","cited_by_count":7,"area":null},{"id":"2605.11161","title":"Interpretability Can Be Actionable","created":"2026-05-11","cited_by_count":7,"area":null},{"id":"2606.07612","title":"Position: Anthropomorphic Misalignment Research Needs Stronger Evidence","created":"2026-05-29","cited_by_count":7,"area":null},{"id":"2308.15605","title":"Benchmarks for Detecting Measurement Tampering","created":"2023-08-29","cited_by_count":6,"area":null},{"id":"2405.00301","title":"Enhanced Language Model Truthfulness with Learnable Intervention and Uncertainty Expression","created":"2024-05-01","cited_by_count":6,"area":null},{"id":"2509.23782","title":"Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2510.08506","title":"Neologism Learning for Controllability and Self-Verbalization","created":"2025-10-09","cited_by_count":6,"area":null},{"id":"2510.14077","title":"ERGO: Entropy-guided Resetting for Generation Optimization in Multi-turn Language Models","created":"2025-10-15","cited_by_count":6,"area":null},{"id":"2510.19127","title":"Steering Autoregressive Music Generation with Recursive Feature Machines","created":"2025-10-21","cited_by_count":6,"area":null},{"id":"2601.03115","title":"Discovering and Causally Validating Emotion-Sensitive Neurons in Large Audio-Language Models","created":"2026-01-06","cited_by_count":6,"area":null},{"id":"2601.19375","title":"Selective Steering: Norm-Preserving Control Through Discriminative Layer Selection","created":"2026-01-27","cited_by_count":6,"area":null},{"id":"2602.03545","title":"Persona Generators: Generating Diverse Synthetic Personas for Arbitrary Contexts","created":"2026-02-03","cited_by_count":6,"area":null},{"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":"2602.11079","title":"Probe-Based Data Attribution: Discovering and Mitigating Undesirable Behaviors in LLM Post-Training","created":"2026-02-11","cited_by_count":6,"area":null},{"id":"2410.02472","title":"Meta-Models: An Architecture for Decoding LLM Behaviors Through Interpreted Embeddings and Natural Language","created":"2024-10-03","cited_by_count":5,"area":null},{"id":"2511.03738","title":"Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs","created":"2025-10-29","cited_by_count":5,"area":null},{"id":"2602.00782","title":"Controlling Repetition in Protein Language Models","created":"2026-01-31","cited_by_count":5,"area":null},{"id":"2604.17465","title":"Language models recognize dropout and Gaussian noise applied to their activations","created":"2026-04-19","cited_by_count":5,"area":null},{"id":"2605.20745","title":"The Hidden Signal of Verifier Strictness: Controlling and Improving Step-Wise Verification via Selective Latent Steering","created":"2026-05-20","cited_by_count":5,"area":null},{"id":"2412.06060","title":"Steering Large Language Models to Evaluate and Amplify Creativity","created":"2024-12-08","cited_by_count":4,"area":null},{"id":"2502.15507","title":"Steering LLMs for Formal Theorem Proving","created":"2025-02-21","cited_by_count":4,"area":null},{"id":"2504.08016","title":"Emergence of psychopathological computations in large language models","created":"2025-04-10","cited_by_count":4,"area":null},{"id":"2505.16505","title":"Sparse Activation Editing for Reliable Instruction Following in Narratives","created":"2025-05-22","cited_by_count":4,"area":null},{"id":"2505.21800","title":"From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2506.06686","title":"Learning Distribution-Wise Control in Representation Space for Language Models","created":"2025-06-07","cited_by_count":4,"area":null}],"next_cursor":"100"}