{"total":62,"rows":[{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2503.11926","title":"Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation","created":"2025-03-14","cited_by_count":384,"area":"lr"},{"id":"2502.02013","title":"Layer by Layer: Uncovering Hidden Representations in Language Models","created":"2025-02-04","cited_by_count":311,"area":null},{"id":"2605.29358","title":"Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet","created":"2026-05-28","cited_by_count":191,"area":"mechinterp"},{"id":"2406.07358","title":"AI Sandbagging: Language Models can Strategically Underperform on Evaluations","created":"2024-06-11","cited_by_count":145,"area":null},{"id":"2407.12404","title":"Analyzing the Generalization and Reliability of Steering Vectors","created":"2024-07-17","cited_by_count":143,"area":"mechinterp"},{"id":"2402.07510","title":"Secret Collusion among AI Agents: Multi-Agent Deception via Steganography","created":"2024-02-12","cited_by_count":113,"area":"agents"},{"id":"2411.11296","title":"Steering Language Model Refusal with Sparse Autoencoders","created":"2024-11-18","cited_by_count":95,"area":"mechinterp"},{"id":"2406.00799","title":"Get my drift? Catching LLM Task Drift with Activation Deltas","created":"2024-06-02","cited_by_count":72,"area":"rag"},{"id":"2402.14433","title":"A Language Model's Guide Through Latent Space","created":"2024-02-22","cited_by_count":43,"area":null},{"id":"2406.19501","title":"Monitoring Latent World States in Language Models with Propositional Probes","created":"2024-06-27","cited_by_count":43,"area":"wm"},{"id":"2410.12949","title":"Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization","created":"2024-10-16","cited_by_count":35,"area":"safety"},{"id":"2412.09563","title":"Does Representation Matter? Exploring Intermediate Layers in Large Language Models","created":"2024-12-12","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":"2407.08039","title":"Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models","created":"2024-07-10","cited_by_count":25,"area":null},{"id":"2506.14261","title":"RL-Obfuscation: Can Language Models Learn to Evade Latent-Space Monitors?","created":"2025-06-17","cited_by_count":24,"area":null},{"id":"2502.17601","title":"Representation Engineering for Large-Language Models: Survey and Research Challenges","created":"2025-02-24","cited_by_count":21,"area":"mechinterp"},{"id":"2406.20086","title":"Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs","created":"2024-06-28","cited_by_count":18,"area":null},{"id":"2410.01174","title":"Towards Inference-time Category-wise Safety Steering for Large Language Models","created":"2024-10-02","cited_by_count":18,"area":"alignment"},{"id":"2506.00823","title":"Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks","created":"2025-06-01","cited_by_count":18,"area":null},{"id":"2505.16491","title":"LLaMAs Have Feelings Too: Unveiling Sentiment and Emotion Representations in LLaMA Models Through Probing","created":"2025-05-22","cited_by_count":15,"area":null},{"id":"2412.16468","title":"The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment","created":"2024-12-21","cited_by_count":13,"area":"alignment"},{"id":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"id":"2505.19610","title":"JailBound: Jailbreaking Internal Safety Boundaries of Vision-Language Models","created":"2025-05-26","cited_by_count":10,"area":"mllm"},{"id":"2506.04250","title":"SafeSteer: Interpretable Safety Steering with Refusal-Evasion in LLMs","created":"2025-06-01","cited_by_count":10,"area":"mechinterp"},{"id":"2404.05971","title":"Does Transformer Interpretability Transfer to RNNs?","created":"2024-04-09","cited_by_count":9,"area":"ssm"},{"id":"2512.00218","title":"Reasoning Under Pressure: How do Training Incentives Influence Chain-of-Thought Monitorability?","created":"2025-11-28","cited_by_count":9,"area":"lr"},{"id":"2601.22588","title":"Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry","created":"2026-01-30","cited_by_count":8,"area":"lr"},{"id":"2504.08820","title":"CAReDiO: Cultural Alignment via Representativeness and Distinctiveness Guided Data Optimization","created":"2025-04-09","cited_by_count":6,"area":null},{"id":"2506.00166","title":"Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment","created":"2025-05-30","cited_by_count":6,"area":"alignment"},{"id":"2603.17199","title":"Catching rationalization in the act: detecting motivated reasoning before and after CoT via activation probing","created":"2026-03-17","cited_by_count":6,"area":"lr"},{"id":"2407.14008","title":"Investigating the Indirect Object Identification circuit in Mamba","created":"2024-07-19","cited_by_count":5,"area":"ssm"},{"id":"2504.08812","title":"Mechanistic Anomaly Detection for \"Quirky\" Language Models","created":"2025-04-09","cited_by_count":5,"area":null},{"id":"2407.18712","title":"Cluster-norm for Unsupervised Probing of Knowledge","created":"2024-07-26","cited_by_count":4,"area":null},{"id":"2604.11061","title":"Pando: Do Interpretability Methods Work When Models Won't Explain Themselves?","created":"2026-04-13","cited_by_count":4,"area":"mechinterp"},{"id":"2502.16385","title":"Toward a Flexible Framework for Linear Representation Hypothesis Using Maximum Likelihood Estimation","created":"2025-02-22","cited_by_count":3,"area":null},{"id":"2504.16871","title":"Exploring How LLMs Capture and Represent Domain-Specific Knowledge","created":"2025-04-23","cited_by_count":3,"area":null},{"id":"2602.05532","title":"Split Personality Training: Revealing Latent Knowledge Through Alternate Personalities","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2602.22719","title":"Interpreting and Steering State-Space Models via Activation Subspace Bottlenecks","created":"2026-02-26","cited_by_count":3,"area":"ssm"},{"id":"2605.00226","title":"Why Do LLMs Struggle in Strategic Play? Broken Links Between Observations, Beliefs, and Actions","created":"2026-04-30","cited_by_count":3,"area":null},{"id":"2609.07876","title":"LLM Layers Immediately Correct Each Other","created":"2026-09-07","cited_by_count":3,"area":"mechinterp"},{"id":"2410.13215","title":"Balancing Label Quantity and Quality for Scalable Elicitation","created":"2024-10-17","cited_by_count":2,"area":null},{"id":"2503.07660","title":"Research Superalignment Should Advance Now with Alternating Competence and Conformity Optimization","created":"2025-03-08","cited_by_count":1,"area":"alignment"},{"id":"2512.04144","title":"RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories","created":"2025-12-03","cited_by_count":1,"area":"safety"},{"id":"2601.12460","title":"TrojanPraise: Jailbreak LLMs via Benign Fine-Tuning","created":"2026-01-18","cited_by_count":1,"area":"safety"},{"id":"2604.18970","title":"Mechanistic Anomaly Detection via Functional Attribution","created":"2026-04-21","cited_by_count":1,"area":"safety"},{"id":"2606.12268","title":"The Impossibility of Eliciting Latent Knowledge","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2508.06592","title":"Towards Integrated Alignment","created":"2025-08-08","cited_by_count":0,"area":"alignment"},{"id":"2508.06827","title":"Who's the Evil Twin? Differential Auditing for Undesired Behavior","created":"2025-08-09","cited_by_count":0,"area":"safety"},{"id":"2601.01011","title":"Intention Collapse: Intention-Level Metrics for Reasoning in Language Models","created":"2026-01-03","cited_by_count":0,"area":"lr"},{"id":"2602.20400","title":"Three Concrete Challenges and Two Hopes for the Safety of Unsupervised Elicitation","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2605.06335","title":"Eliciting associations between clinical variables from LLMs via comparison questions across populations","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.11448","title":"Deep Minds and Shallow Probes","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.28825","title":"MechELK: A Mechanistic Interpretability Framework for Eliciting Latent Knowledge in Large Language Models","created":"2026-04-07","cited_by_count":0,"area":"lr"},{"id":"2606.03645","title":"The Shape of Addition: Geometric Structures of Arithmetic in Large Language Models","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.09306","title":"Exposure is not manifestation: measurement target and output resolution jointly determine which behavioural-faithfulness evaluator wins","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2609.21996","title":"A Lie Detector Test for Language Models: Reading Knowledge a Model Won't Reveal","created":"2026-09-18","cited_by_count":0,"area":"safety"},{"id":"2609.31401","title":"Decodable In-Context State and Model Output Across Training","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.36316","title":"Training LLMs to Verbalize Evaluation Awareness","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.04737","title":"PyINE: A Framework for Scalable Elicitation and Oversight via Code Execution","created":"2026-10-03","cited_by_count":0,"area":"lr"},{"id":"2610.13928","title":"AI Models Can Provably Hide Arbitrary Capabilities","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.18727","title":"On the Monitorability of Natural Language Autoencoders: Identification vs Discrimination","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}