{"total":164,"rows":[{"id":"2310.06824","title":"The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets","created":"2023-10-10","cited_by_count":712,"area":null},{"id":"2403.19647","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","created":"2024-03-28","cited_by_count":435,"area":null},{"id":"2306.12001","title":"An Overview of Catastrophic AI Risks","created":"2023-06-21","cited_by_count":222,"area":null},{"id":"2404.03592","title":"ReFT: Representation Finetuning for Language Models","created":"2024-04-04","cited_by_count":197,"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":"2309.17410","title":"Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks","created":"2023-09-29","cited_by_count":158,"area":null},{"id":"2306.17806","title":"Stay on topic with Classifier-Free Guidance","created":"2023-06-30","cited_by_count":91,"area":null},{"id":"2403.14472","title":"Detoxifying Large Language Models via Knowledge Editing","created":"2024-03-21","cited_by_count":87,"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":"2506.11618","title":"Convergent Linear Representations of Emergent Misalignment","created":"2025-06-13","cited_by_count":71,"area":null},{"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":"2402.09631","title":"Representation Surgery: Theory and Practice of Affine Steering","created":"2024-02-15","cited_by_count":50,"area":null},{"id":"2408.10920","title":"Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations","created":"2024-08-20","cited_by_count":47,"area":null},{"id":"2402.12560","title":"CausalGym: Benchmarking causal interpretability methods on linguistic tasks","created":"2024-02-19","cited_by_count":46,"area":null},{"id":"2507.16795","title":"Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning","created":"2025-07-22","cited_by_count":39,"area":null},{"id":"2402.16382","title":"Immunization against harmful fine-tuning attacks","created":"2024-02-26","cited_by_count":35,"area":null},{"id":"2406.11194","title":"In-Context Editing: Learning Knowledge from Self-Induced Distributions","created":"2024-06-17","cited_by_count":34,"area":null},{"id":"2410.04332","title":"Gradient Routing: Masking Gradients to Localize Computation in Neural Networks","created":"2024-10-06","cited_by_count":34,"area":null},{"id":"2510.13290","title":"To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models","created":"2025-10-15","cited_by_count":29,"area":null},{"id":"2310.11958","title":"Emptying the Ocean with a Spoon: Should We Edit Models?","created":"2023-10-18","cited_by_count":27,"area":null},{"id":"2406.11107","title":"Exploring Safety-Utility Trade-Offs in Personalized Language Models","created":"2024-06-17","cited_by_count":27,"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":"2307.15054","title":"A Geometric Notion of Causal Probing","created":"2023-07-27","cited_by_count":25,"area":null},{"id":"2409.09951","title":"Optimal ablation for interpretability","created":"2024-09-16","cited_by_count":25,"area":null},{"id":"2310.18913","title":"Debiasing Algorithm through Model Adaptation","created":"2023-10-29","cited_by_count":24,"area":null},{"id":"2407.04690","title":"Missed Causes and Ambiguous Effects: Counterfactuals Pose Challenges for Interpreting Neural Networks","created":"2024-07-05","cited_by_count":23,"area":null},{"id":"2411.07404","title":"Controllable Context Sensitivity and the Knob Behind It","created":"2024-11-11","cited_by_count":23,"area":null},{"id":"2310.12611","title":"Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model","created":"2023-10-19","cited_by_count":22,"area":null},{"id":"2403.08994","title":"Ethos: Rectifying Language Models in Orthogonal Parameter Space","created":"2024-03-13","cited_by_count":20,"area":null},{"id":"2405.15454","title":"LiSeCo: Linear Semantic Control for Language Generation","created":"2024-05-24","cited_by_count":20,"area":null},{"id":"2404.11534","title":"Decomposing and Editing Predictions by Modeling Model Computation","created":"2024-04-17","cited_by_count":19,"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":"2410.08113","title":"Robust AI-Generated Text Detection by Restricted Embeddings","created":"2024-10-10","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":"2403.09053","title":"Towards a theory of model distillation","created":"2024-03-14","cited_by_count":15,"area":null},{"id":"2404.09454","title":"Utility-Fairness Trade-Offs and How to Find Them","created":"2024-04-15","cited_by_count":15,"area":null},{"id":"2311.07682","title":"Fuse to Forget: Bias Reduction and Selective Memorization through Model Fusion","created":"2023-11-13","cited_by_count":13,"area":null},{"id":"2311.04354","title":"Uncovering Intermediate Variables in Transformers using Circuit Probing","created":"2023-11-07","cited_by_count":12,"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":"2505.22586","title":"Precise In-Parameter Concept Erasure in Large Language Models","created":"2025-05-28","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":"2405.06919","title":"Automating Thematic Analysis: How LLMs Analyse Controversial Topics","created":"2024-05-11","cited_by_count":10,"area":null},{"id":"2510.02340","title":"Can Prompts Rewind Time for LLMs? Evaluating the Effectiveness of Prompted Knowledge Cutoffs","created":"2025-09-26","cited_by_count":10,"area":null},{"id":"2504.10227","title":"Probing then Editing Response Personality of Large Language Models","created":"2025-04-14","cited_by_count":9,"area":null},{"id":"2412.13341","title":"Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing","created":"2024-12-17","cited_by_count":8,"area":null},{"id":"2509.18868","title":"Memory in Large Language Models: Mechanisms, Evaluation and Evolution","created":"2025-09-23","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":"2308.15605","title":"Benchmarks for Detecting Measurement Tampering","created":"2023-08-29","cited_by_count":6,"area":null},{"id":"2310.11991","title":"Removing Spurious Concepts from Neural Network Representations via Joint Subspace Estimation","created":"2023-10-18","cited_by_count":6,"area":null},{"id":"2502.15277","title":"Analyzing the Inner Workings of Transformers in Compositional Generalization","created":"2025-02-21","cited_by_count":6,"area":null},{"id":"2503.20098","title":"Fundamental Limits of Perfect Concept Erasure","created":"2025-03-25","cited_by_count":6,"area":null},{"id":"2506.12217","title":"From Emergence to Control: Probing and Modulating Self-Reflection in Language Models","created":"2025-06-13","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":"2412.07334","title":"Frame Representation Hypothesis: Multi-Token LLM Interpretability and Concept-Guided Text Generation","created":"2024-12-10","cited_by_count":5,"area":null},{"id":"2602.17598","title":"The Cascade Equivalence Hypothesis: When Do Speech LLMs Behave Like ASR$\\rightarrow$LLM Pipelines?","created":"2026-02-19","cited_by_count":5,"area":null},{"id":"2312.06499","title":"TaCo: Targeted Concept Erasure Prevents Non-Linear Classifiers From Detecting Protected Attributes","created":"2023-12-11","cited_by_count":4,"area":null},{"id":"2402.11355","title":"A Practical Method for Generating String Counterfactuals","created":"2024-02-17","cited_by_count":4,"area":null},{"id":"2406.09855","title":"On the Encoding of Gender in Transformer-based ASR Representations","created":"2024-06-14","cited_by_count":4,"area":null},{"id":"2409.02228","title":"Unforgettable Generalization in Language Models","created":"2024-09-03","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},{"id":"2506.10703","title":"Preserving Task-Relevant Information Under Linear Concept Removal","created":"2025-06-12","cited_by_count":4,"area":null},{"id":"2506.11673","title":"Improving Causal Interventions in Amnesic Probing with Mean Projection or LEACE","created":"2025-06-13","cited_by_count":4,"area":null},{"id":"2402.00711","title":"Explaining Text Classifiers with Counterfactual Representations","created":"2024-02-01","cited_by_count":3,"area":null},{"id":"2403.16584","title":"Can Large Language Models (or Humans) Disentangle Text?","created":"2024-03-25","cited_by_count":3,"area":null},{"id":"2406.17809","title":"Towards a Science Exocortex","created":"2024-06-24","cited_by_count":3,"area":null},{"id":"2507.12341","title":"Nonlinear Concept Erasure: a Density Matching Approach","created":"2025-07-16","cited_by_count":3,"area":null},{"id":"2605.11410","title":"What Do EEG Foundation Models Capture from Human Brain Signals?","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2403.02327","title":"Model Lakes","created":"2024-03-04","cited_by_count":2,"area":null},{"id":"2406.00787","title":"Applying Intrinsic Debiasing on Downstream Tasks: Challenges and Considerations for Machine Translation","created":"2024-06-02","cited_by_count":2,"area":null},{"id":"2412.00789","title":"A Cognac Shot To Forget Bad Memories: Corrective Unlearning for Graph Neural Networks","created":"2024-12-01","cited_by_count":2,"area":null},{"id":"2501.10150","title":"Dual Debiasing: Remove Stereotypes and Keep Factual Gender for Fair Language Modeling and Translation","created":"2025-01-17","cited_by_count":2,"area":null},{"id":"2501.13818","title":"Ensuring Medical AI Safety: Interpretability-Driven Detection and Mitigation of Spurious Model Behavior and Associated Data","created":"2025-01-23","cited_by_count":2,"area":null},{"id":"2505.03997","title":"Quiet Feature Learning in Algorithmic Tasks","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2505.20343","title":"Do LLMs have a Gender (Entropy) Bias?","created":"2025-05-24","cited_by_count":2,"area":null},{"id":"2601.10700","title":"LIBERTy: A Causal Framework for Benchmarking Concept-Based Explanations of LLMs with Structural Counterfactuals","created":"2026-01-15","cited_by_count":2,"area":null},{"id":"2603.07529","title":"Obliviator Reveals the Cost of Nonlinear Guardedness in Concept Erasure","created":"2026-03-08","cited_by_count":2,"area":null},{"id":"2605.01381","title":"A framework for analyzing concept representations in neural models","created":"2026-05-02","cited_by_count":2,"area":null},{"id":"2605.05715","title":"Decodable but Not Corrected by Fixed Residual-Stream Linear Steering: Evidence from Medical LLM Failure Regimes","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2606.06647","title":"The Identity Trap in EEG Foundation Models: A Diagnostic Audit","created":"2026-06-04","cited_by_count":2,"area":null},{"id":"2608.11735","title":"Locating and Controlling Implicit Personalization in Large Language Models","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2505.05492","title":"DetoxAI: a Python Toolkit for Debiasing Deep Learning Models in Computer Vision","created":"2025-05-02","cited_by_count":1,"area":null},{"id":"2507.01234","title":"The Medium Is Not the Message: Deconfounding Document Embeddings via Linear Concept Erasure","created":"2025-07-01","cited_by_count":1,"area":null},{"id":"2510.13849","title":"Language steering in latent space to mitigate unintended code-switching","created":"2025-10-11","cited_by_count":1,"area":null},{"id":"2601.23157","title":"No More, No Less: Least-Privilege Language Models","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2603.00047","title":"What Is the Alignment Tax?","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2604.23452","title":"From Edges to Depth: Probing the Spatial Hierarchy in Vision Transformers","created":"2026-04-25","cited_by_count":1,"area":null},{"id":"2605.06640","title":"Concept-Based Abductive and Contrastive Explanations for Behaviors of Vision Models","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.09195","title":"The Geometry of Forgetting: Temporal Knowledge Drift as an Independent Axis in LLM Representations","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2605.25891","title":"Causal Tongue-Tie: LLMs Can Encode Causal Direction, But Their Yes/No Outputs Fail to Express","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2605.27676","title":"Unsupervised Identification and Removal of Spurious Correlations During Fine-Tuning","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2606.05165","title":"STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2606.13720","title":"Refusal Beyond a Single Direction: A Preliminary Comparison of Diff-in-Means and INLP","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2608.06891","title":"SkillEval: Decomposing Agent Skill Quality into Interpretable Signals","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2608.10566","title":"Iterative Erasure Count Is Not an Affine-Invariant Concept Dimension","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2609.00823","title":"Polished but Unresolved: Identifying Late-Stage Pressure States in Long-Horizon Tool-Use Agents","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2609.14759","title":"Refusal Reads Only a Slice of What the Model Knows: Harm-Keyed Routing and Its Exceptions Across Model Families","created":"2026-09-13","cited_by_count":1,"area":null},{"id":"2609.16247","title":"The Pain Axis: LLMs Represent Self-Directed Harm and Act on It","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2312.00584","title":"The Ethics of Automating Legal Actors","created":"2023-12-01","cited_by_count":0,"area":null},{"id":"2403.16142","title":"What Happens to a Dataset Transformed by a Projection-based Concept Removal Method?","created":"2024-03-24","cited_by_count":0,"area":null},{"id":"2407.19345","title":"Inference-Time Selective Debiasing to Enhance Fairness in Text Classification Models","created":"2024-07-27","cited_by_count":0,"area":null}],"next_cursor":"100"}