{"total":345,"rows":[{"id":"2508.17511","title":"School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs","created":"2025-08-24","cited_by_count":66,"area":"alignment"},{"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":"2510.04340","title":"Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time","created":"2025-10-05","cited_by_count":43,"area":null},{"id":"2510.05024","title":"Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment","created":"2025-10-06","cited_by_count":43,"area":"alignment"},{"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":"2509.03730","title":"The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs","created":"2025-09-03","cited_by_count":36,"area":null},{"id":"2509.23055","title":"Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate","created":"2025-09-27","cited_by_count":29,"area":"agents"},{"id":"2511.00617","title":"Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering","created":"2025-11-01","cited_by_count":29,"area":"mechinterp"},{"id":"2510.13900","title":"Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences","created":"2025-10-14","cited_by_count":28,"area":null},{"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":"2508.04826","title":"Persistent Instability in LLM's Personality Measurements: Effects of Scale, Reasoning, and Conversation History","created":"2025-08-06","cited_by_count":26,"area":"lr"},{"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":"2511.01689","title":"Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI","created":"2025-11-03","cited_by_count":24,"area":"alignment"},{"id":"2601.16644","title":"Sycophancy Hides Linearly in the Attention Heads","created":"2026-01-23","cited_by_count":23,"area":null},{"id":"2602.01002","title":"How RLHF Amplifies Sycophancy","created":"2026-02-01","cited_by_count":23,"area":"alignment"},{"id":"2511.05408","title":"Steering Language Models with Weight Arithmetic","created":"2025-11-07","cited_by_count":20,"area":null},{"id":"2605.02087","title":"Model Spec Midtraining: Improving How Alignment Training Generalizes","created":"2026-05-03","cited_by_count":20,"area":null},{"id":"2602.04863","title":"Subliminal Effects in Your Data: A General Mechanism via Log-Linearity","created":"2026-02-04","cited_by_count":19,"area":null},{"id":"2601.04025","title":"Simulated Students in Tutoring Dialogues: Substance or Illusion?","created":"2026-01-07","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":"2510.27062","title":"Consistency Training Helps Stop Sycophancy and Jailbreaks","created":"2025-10-31","cited_by_count":16,"area":"safety"},{"id":"2603.05487","title":"Observing and Controlling Features in Vision-Language-Action Models","created":"2026-03-05","cited_by_count":16,"area":"vla"},{"id":"2605.21778","title":"What Counts as AI Sycophancy? A Taxonomy and Expert Survey of a Fragmented Construct","created":"2026-05-20","cited_by_count":16,"area":null},{"id":"2508.06249","title":"In-Training Defenses against Emergent Misalignment in Language Models","created":"2025-08-08","cited_by_count":15,"area":"alignment"},{"id":"2510.25536","title":"TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulation","created":"2025-10-29","cited_by_count":15,"area":null},{"id":"2511.06626","title":"Spilling the Beans: Teaching LLMs to Self-Report Their Hidden Objectives","created":"2025-11-10","cited_by_count":15,"area":"agents"},{"id":"2512.19027","title":"Recontextualization Mitigates Specification Gaming without Modifying the Specification","created":"2025-12-22","cited_by_count":14,"area":null},{"id":"2604.25783","title":"Subliminal Steering: Stronger Encoding of Hidden Signals","created":"2026-04-28","cited_by_count":14,"area":"mechinterp"},{"id":"2509.25137","title":"The Era of Real-World Human Interaction: RL from User Conversations","created":"2025-09-29","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":"2606.00995","title":"Subliminal Learning Is Steering Vector Distillation","created":"2026-05-31","cited_by_count":13,"area":"mechinterp"},{"id":"2606.14199","title":"OdysSim: Building Foundation Models for Human Behavior Simulation","created":"2026-06-12","cited_by_count":13,"area":null},{"id":"2510.01591","title":"CLUE: Non-parametric Verification from Experience via Hidden-State Clustering","created":"2025-10-02","cited_by_count":12,"area":null},{"id":"2510.20956","title":"Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training","created":"2025-10-23","cited_by_count":12,"area":"lr"},{"id":"2511.06419","title":"MONICA: Real-Time Monitoring and Calibration of Chain-of-Thought Sycophancy in Large Reasoning Models","created":"2025-11-09","cited_by_count":12,"area":"lr"},{"id":"2601.10825","title":"Reasoning Models Generate Societies of Thought","created":"2026-01-15","cited_by_count":12,"area":"lr"},{"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":"2511.04962","title":"Too Good to be Bad: On the Failure of LLMs to Role-Play Villains","created":"2025-11-07","cited_by_count":11,"area":null},{"id":"2601.04745","title":"KnowMe-Bench: Benchmarking Person Understanding for Lifelong Digital Companions","created":"2026-01-08","cited_by_count":11,"area":null},{"id":"2604.09212","title":"SPASM: Stable Persona-driven Agent Simulation for Multi-turn Dialogue Generation","created":"2026-04-10","cited_by_count":11,"area":"agents"},{"id":"2510.03659","title":"Does higher interpretability imply better utility? A Pairwise Analysis on Sparse Autoencoders","created":"2025-10-04","cited_by_count":10,"area":"mechinterp"},{"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":"2512.13674","title":"Towards Interactive Intelligence for Digital Humans","created":"2025-12-15","cited_by_count":10,"area":null},{"id":"2604.17031","title":"Where is the Mind? Persona Vectors and LLM Individuation","created":"2026-04-18","cited_by_count":10,"area":null},{"id":"2606.22936","title":"When Agents Commit Too Soon: Diagnosing Premature Commitment in LLM Agents","created":"2026-06-22","cited_by_count":10,"area":"agents"},{"id":"2511.08525","title":"Investigating CoT Monitorability in Large Reasoning Models","created":"2025-11-11","cited_by_count":9,"area":"lr"},{"id":"2511.21399","title":"Steering Awareness: Detecting Activation Steering from Within","created":"2025-11-26","cited_by_count":9,"area":"mechinterp"},{"id":"2512.17639","title":"Linear Personality Probing and Steering in LLMs: A Big Five Study","created":"2025-12-19","cited_by_count":9,"area":null},{"id":"2607.00415","title":"A Mechanistic View of Authority Hierarchy in LLM Sycophancy","created":"2026-07-01","cited_by_count":9,"area":null},{"id":"2509.13588","title":"CoBRA: Programming Cognitive Bias in Social Agents Using Classic Social Science Experiments","created":"2025-09-16","cited_by_count":8,"area":"agents"},{"id":"2510.08211","title":"LLMs Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions","created":"2025-10-09","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":"2602.06801","title":"On the Non-Identifiability of Steering Vectors in Large Language Models","created":"2026-02-06","cited_by_count":8,"area":"mechinterp"},{"id":"2602.14869","title":"Concept Influence: Leveraging Interpretability to Improve Performance and Efficiency in Training Data Attribution","created":"2026-02-16","cited_by_count":8,"area":"mechinterp"},{"id":"2603.16643","title":"Good Arguments Against the People Pleasers: How Reasoning Mitigates (Yet Masks) LLM Sycophancy","created":"2026-03-17","cited_by_count":8,"area":"lr"},{"id":"2604.02423","title":"SWAY: A Counterfactual Computational Linguistic Approach to Measuring and Mitigating Sycophancy","created":"2026-04-02","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":"2605.12798","title":"Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer","created":"2026-05-12","cited_by_count":8,"area":null},{"id":"2509.07961","title":"Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare","created":"2025-09-09","cited_by_count":7,"area":"alignment"},{"id":"2510.15987","title":"AlgoTrace: Algorithmic Primitives and Compositional Geometry of Reasoning in Language Models","created":"2025-10-13","cited_by_count":7,"area":"lr"},{"id":"2602.05176","title":"Among Us: Measuring and Mitigating Malicious Contributions in Model Collaboration Systems","created":"2026-02-05","cited_by_count":7,"area":"agents"},{"id":"2603.21396","title":"Mechanisms of Introspective Awareness","created":"2026-03-22","cited_by_count":7,"area":"mechinterp"},{"id":"2604.08524","title":"What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal","created":"2026-04-09","cited_by_count":7,"area":"alignment"},{"id":"2604.24693","title":"Contextual Linear Activation Steering of Language Models","created":"2026-04-27","cited_by_count":7,"area":"mechinterp"},{"id":"2605.00842","title":"Understanding Emergent Misalignment via Feature Superposition Geometry","created":"2026-04-07","cited_by_count":7,"area":"mechinterp"},{"id":"2605.11161","title":"Interpretability Can Be Actionable","created":"2026-05-11","cited_by_count":7,"area":null},{"id":"2605.13329","title":"Tracing Persona Vectors Through LLM Pretraining","created":"2026-05-13","cited_by_count":7,"area":null},{"id":"2510.02324","title":"Hallucination reduction with CASAL: Contrastive Activation Steering For Amortized Learning","created":"2025-09-25","cited_by_count":6,"area":"moe"},{"id":"2511.18284","title":"What Can We Actually Steer? A Multi-Behavior Study of Activation Control","created":"2025-11-23","cited_by_count":6,"area":"mechinterp"},{"id":"2601.05437","title":"Tracing Moral Foundations in Large Language Models","created":"2026-01-09","cited_by_count":6,"area":"mechinterp"},{"id":"2601.09269","title":"RISER: Orchestrating Latent Reasoning Skills for Adaptive Activation Steering","created":"2026-01-14","cited_by_count":6,"area":"lr"},{"id":"2601.15220","title":"Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models","created":"2026-01-21","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":"2602.11079","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":"2602.16931","title":"Narrow Fine-Tuning Erodes Safety Alignment in Vision-Language Agents","created":"2026-02-18","cited_by_count":6,"area":"mllm"},{"id":"2603.06745","title":"Enhancing Instruction Following of LLMs via Activation Steering with Dynamic Rejection","created":"2026-03-06","cited_by_count":6,"area":"mechinterp"},{"id":"2603.21398","title":"Persona Vectors in Games: Measuring and Steering Strategies via Activation Vectors","created":"2026-03-22","cited_by_count":6,"area":null},{"id":"2605.02946","title":"RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs","created":"2026-05-01","cited_by_count":6,"area":"alignment"},{"id":"2605.10664","title":"Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions","created":"2026-05-11","cited_by_count":6,"area":"mechinterp"},{"id":"2606.04071","title":"Covert Influence Between Language Models","created":"2026-06-02","cited_by_count":6,"area":null},{"id":"2607.07003","title":"Dissociating the Internal Representations of Sycophancy in LLMs","created":"2026-07-08","cited_by_count":6,"area":"mechinterp"},{"id":"2508.20015","title":"Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment","created":"2025-08-27","cited_by_count":5,"area":null},{"id":"2511.21722","title":"German General Social Survey Personas: A Survey-Derived Persona Prompt Collection for Population-Aligned LLM Studies","created":"2025-11-19","cited_by_count":5,"area":null},{"id":"2601.23081","title":"Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures","created":"2026-01-30","cited_by_count":5,"area":"safety"},{"id":"2602.07164","title":"Your Language Model Secretly Contains Personality Subnetworks","created":"2026-02-06","cited_by_count":5,"area":null},{"id":"2602.15847","title":"Do Personality Traits Interfere? Geometric Limitations of Steering in Large Language Models","created":"2026-01-23","cited_by_count":5,"area":"mechinterp"},{"id":"2603.13249","title":"Steering at the Source: Style Modulation Heads for Robust Persona Control","created":"2026-02-24","cited_by_count":5,"area":"mechinterp"},{"id":"2604.13051","title":"The Consciousness Cluster: Emergent preferences of Models that Claim to be Conscious","created":"2026-03-17","cited_by_count":5,"area":"alignment"},{"id":"2604.24881","title":"Latent Agents: A Post-Training Procedure for Internalized Multi-Agent Debate","created":"2026-04-27","cited_by_count":5,"area":"lr"},{"id":"2605.01167","title":"Minimizing Collateral Damage in Activation Steering","created":"2026-05-01","cited_by_count":5,"area":"mechinterp"},{"id":"2605.03907","title":"Steer Like the LLM: Activation Steering that Mimics Prompting","created":"2026-05-05","cited_by_count":5,"area":"mechinterp"},{"id":"2605.24279","title":"ContextEcho: A Benchmark for Persona Drift in Long Agentic-Coding Sessions","created":"2026-05-22","cited_by_count":5,"area":"agents"},{"id":"2509.03626","title":"Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILE","created":"2025-09-03","cited_by_count":4,"area":"rag"},{"id":"2509.04794","title":"Personality as a Probe for LLM Evaluation: Method Trade-offs and Downstream Effects","created":"2025-09-05","cited_by_count":4,"area":"agents"},{"id":"2509.26495","title":"OffTopicEval: When Large Language Models Enter the Wrong Chat, Almost Always!","created":"2025-09-30","cited_by_count":4,"area":"agents"},{"id":"2510.08203","title":"Memory Retrieval and Consolidation in Large Language Models through Function Tokens","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2601.19847","title":"Identifying and Transferring Reasoning-Critical Neurons: Improving LLM Inference Reliability via Activation Steering","created":"2026-01-27","cited_by_count":4,"area":"lr"},{"id":"2602.04925","title":"Internalizing LLM Reasoning via Discovery and Replay of Latent Actions","created":"2026-02-04","cited_by_count":4,"area":"lr"}],"next_cursor":"100"}