{"total":90,"rows":[{"id":"2607.15495","title":"Verbalizable Representations Form a Global Workspace in Language Models","created":"2026-07-16","cited_by_count":75,"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":"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":"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":"2602.02613","title":"Exploring Silicon-Based Societies: An Early Study of the Moltbook Agent Community","created":"2026-02-02","cited_by_count":13,"area":"agents"},{"id":"2601.20834","title":"Linear representations in language models can change dramatically over a conversation","created":"2026-01-28","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":"2604.09839","title":"Steered LLM Activations are Non-Surjective","created":"2026-04-10","cited_by_count":8,"area":"mechinterp"},{"id":"2602.11328","title":"Evaluating Alignment of Behavioral Dispositions in LLMs","created":"2026-02-11","cited_by_count":7,"area":"alignment"},{"id":"2605.13329","title":"Tracing Persona Vectors Through LLM Pretraining","created":"2026-05-13","cited_by_count":7,"area":null},{"id":"2605.05980","title":"TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering","created":"2026-05-07","cited_by_count":6,"area":"lr"},{"id":"2605.13829","title":"Negation Neglect: When models fail to learn negations in training","created":"2026-05-13","cited_by_count":6,"area":null},{"id":"2606.30571","title":"Attractor States Emerge in Multi-Turn LLM Conversations","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2603.00024","title":"Personalization Increases Affective Alignment but Has Role-Dependent Effects on Epistemic Independence in LLMs","created":"2026-02-03","cited_by_count":5,"area":null},{"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":"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":"2604.13076","title":"Alignment midtraining for animals","created":"2026-03-21","cited_by_count":4,"area":null},{"id":"2605.21006","title":"Playing Devil's Advocate: Off-the-Shelf Persona Vectors Rival Targeted Steering for Sycophancy","created":"2026-05-20","cited_by_count":4,"area":null},{"id":"2605.30169","title":"Dissociative Identity: Language Model Agents Lack Grounding for Reputation Mechanisms","created":"2026-05-28","cited_by_count":4,"area":"agents"},{"id":"2607.07916","title":"Persona Cartography: Charting Language Model Personality Traits in Weight Space","created":"2026-07-08","cited_by_count":4,"area":null},{"id":"2608.10218","title":"Mind Viruses: Self-Propagating Ideas in Multi-Agent LLM Systems","created":"2026-08-10","cited_by_count":4,"area":"agents"},{"id":"2601.15334","title":"No Reliable Evidence of Self-Reported Sentience in Small Large Language Models","created":"2026-01-20","cited_by_count":3,"area":null},{"id":"2605.13339","title":"Probing Persona-Dependent Preferences in Language Models","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2605.31328","title":"Reinforcement Learning Can Amplify Emergent Misalignment from Harmless Rewards","created":"2026-05-29","cited_by_count":3,"area":"alignment"},{"id":"2607.21356","title":"Emergent Misalignment Recruits a Pre-existing Persona Subspace","created":"2026-07-23","cited_by_count":3,"area":"alignment"},{"id":"2608.21242","title":"Affective Context Amplifies Sycophancy in LLM Responses","created":"2026-08-21","cited_by_count":3,"area":null},{"id":"2603.00048","title":"MOSAIC: Unveiling the Moral, Social and Individual Dimensions of Large Language Models","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2604.12016","title":"Identity as Attractor: Geometric Evidence for Persistent Agent Architecture in LLM Activation Space","created":"2026-04-13","cited_by_count":2,"area":"agents"},{"id":"2606.01196","title":"Low-Resource Safety Failures Are Action Failures, Not Representation Failures","created":"2026-05-31","cited_by_count":2,"area":"alignment"},{"id":"2606.12360","title":"Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2607.00918","title":"From Personas to Plot: Character-Grounded Multi-Agent Story Generation for Long-Form Narratives","created":"2026-07-01","cited_by_count":2,"area":"agents"},{"id":"2607.28818","title":"Best Friends, Not Forever: Evaluating Long-Horizon Persona Collapse and Behavioral Drift in AI Companions","created":"2026-07-30","cited_by_count":2,"area":null},{"id":"2609.37616","title":"Authority Bias in Language Models: Source Deference and User Agreement Are Not Interchangeable","created":"2026-09-29","cited_by_count":2,"area":null},{"id":"2602.00851","title":"Persuasion Propagation: Does Persuasion Change AI Agent Behavior?","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2602.01689","title":"What LLMs Think When You Don't Tell Them What to Think About?","created":"2026-02-02","cited_by_count":1,"area":"lr"},{"id":"2602.11358","title":"When Models Examine Themselves: Vocabulary-Activation Correspondence in Self-Referential Processing","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2603.18893","title":"Quantitative Introspection in Language Models: Tracking Emotive States Across Conversation","created":"2026-03-19","cited_by_count":1,"area":"mechinterp"},{"id":"2604.11120","title":"Persona Non Grata: Single-Method Safety Evaluation Is Incomplete for Persona-Imbued LLMs","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2606.07513","title":"Agentopia: Long-Term Life Simulation and Learning in Agent Societies","created":"2026-06-05","cited_by_count":1,"area":"agents"},{"id":"2606.15420","title":"Constitutional Value Potentials: reading and steering internal priority margins in language models","created":"2026-06-13","cited_by_count":1,"area":null},{"id":"2606.28548","title":"Turn-Averaged SAEs for Feature Discovery and Long-Context Attribution","created":"2026-06-26","cited_by_count":1,"area":"mechinterp"},{"id":"2607.03640","title":"Revealing Hidden Model Behaviors with Task-Specific Self-Reports","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2608.00023","title":"Role Steering of Language Models for Social Simulations","created":"2026-07-09","cited_by_count":1,"area":"agents"},{"id":"2608.11025","title":"Data Attribution of Emergent Misalignment with Persona Features","created":"2026-08-11","cited_by_count":1,"area":"mechinterp"},{"id":"2608.13482","title":"Synthetic Persona Pretraining: Alignment from Token Zero","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2608.26178","title":"AI Revealed Preferences","created":"2026-08-17","cited_by_count":1,"area":"alignment"},{"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":"2609.23935","title":"Measuring the Assistant's Harmlessness Preferences on the User Turn","created":"2026-09-20","cited_by_count":1,"area":null},{"id":"2603.13378","title":"Do Large Language Models Get Caught in Hofstadter-Mobius Loops?","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2604.02677","title":"Human Thinking under Plural LLM Assistance: Mathematical Problem Solving and Open-Ended Writing","created":"2026-04-03","cited_by_count":0,"area":"lr"},{"id":"2605.05080","title":"The Shared Latent Structure of LLM Psychometric Responses","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.06196","title":"The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.09391","title":"Do Linear Probes Generalize Better in Persona Coordinates?","created":"2026-05-10","cited_by_count":0,"area":"mechinterp"},{"id":"2605.10633","title":"Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMs","created":"2026-05-11","cited_by_count":0,"area":"safety"},{"id":"2605.11712","title":"Toward Stable Value Alignment: Introducing Independent Modules for Consistent Value Guidance","created":"2026-05-12","cited_by_count":0,"area":"alignment"},{"id":"2605.20382","title":"Do as I Say, Not as I Do: Instruction-Induction Conflict in LLMs","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.28647","title":"The Ethics of LLM Sandbox and Persona Dynamics","created":"2026-05-27","cited_by_count":0,"area":"safety"},{"id":"2605.28969","title":"Beyond Recall: Behavioral Specification as an Interpretive Layer for AI Personalization","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.14695","title":"Persona-Pruner: Sculpting Lightweight Models for Role-Playing","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2606.21843","title":"Measuring What Persists: Conditioning Mechanisms and a Geometric Framework for AI Agent Identity","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2607.09842","title":"From Direction to Magnitude: How Multimodal Instruction-Tuning Reorganizes the Geometric Encoding of Identity-Specifying Prompts in Transformer Hidden States","created":"2026-07-10","cited_by_count":0,"area":"lr"},{"id":"2607.13162","title":"What Models Express, Suppress, and Resist: Auditing Open-Weight LLMs with Persona Vectors","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.25057","title":"Psychological Influences of Conversational AI: Research and Design Directions for Reducing Harm and Promoting Well-Being","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2608.02957","title":"Inverted Detection and Control in Steering Vectors","created":"2026-08-03","cited_by_count":0,"area":"mechinterp"},{"id":"2608.03044","title":"Emulate or Estimate? The Divergent Strengths of Base and Post-Trained Language Models for Opinion Simulation","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.07852","title":"\"Many Are My Names\": The Anatomy of the Assistant and Its Personas via Sparse Autoencoders","created":"2026-08-08","cited_by_count":0,"area":"mechinterp"},{"id":"2608.20344","title":"Beyond Raw Transcripts: Structured Persona Extraction for LLM-Based Digital Twins","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2608.25977","title":"When Personality Meets Quantization: A Layer-wise MBTI Analysis of Quantized LLMs","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.00192","title":"LLM-Driven Autonomous Vehicles Inherit Human Driver Biases in Pedestrian Yielding: Results and Implications From A New Benchmark","created":"2026-08-31","cited_by_count":0,"area":"driving"},{"id":"2609.00608","title":"Investigating Assistant Bias in LLM User Simulators Using a Role Vector","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.02893","title":"Probe Generalization as Subspace Selection for OOD Deception Detection","created":"2026-07-01","cited_by_count":0,"area":"mechinterp"},{"id":"2609.06851","title":"You Are What You Read: Misalignment via In-Context Persona Induction","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.06951","title":"Steering Interference Reflects the Model's Defaults, Not the Behavior Directions","created":"2026-09-07","cited_by_count":0,"area":"mechinterp"},{"id":"2609.08173","title":"Key Path Identification for Resolving Knowledge Conflicts via SAE-based Steering","created":"2026-09-08","cited_by_count":0,"area":"mechinterp"},{"id":"2609.10883","title":"Story Imprinting: AI Assistants Absorb Traits from Human Characters They Resemble","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.11758","title":"RAG-Safety-Bench: Reliable Evaluation of Retrieval-Augmented LLM Safety","created":"2026-09-10","cited_by_count":0,"area":"rag"},{"id":"2609.22607","title":"Pretrained Persona Mixture Models and Tandem Models for Human Simulation","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.24066","title":"Efficient Reasoning Exploration via State-Conditioned Latent Steering with Progress Guidance","created":"2026-09-21","cited_by_count":0,"area":"lr"},{"id":"2609.25021","title":"\"As a Language Model...\": Chat Template Switches LLM Self-Referential Voice and Activation Steering Reproduces It","created":"2026-08-09","cited_by_count":0,"area":"mechinterp"},{"id":"2609.32758","title":"How Far Do Persona Effects Generalize in Language Models?","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.35618","title":"From cacophony to hierarchy: a principled framework for assessing AI consciousness","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.39807","title":"Stress-Testing LLM Lie Detectors: Role-Play Failures and Spurious Correlations","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39882","title":"LLM Persona Unlearning","created":"2026-09-30","cited_by_count":0,"area":"safety"},{"id":"2610.01490","title":"The Persona Is Still There, but Who Is Speaking? Latent Identity Reversion in Persistent AI Agents","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.09384","title":"The Persona Hierarchy Model: Understanding Contextual Generalization in Fine-Tuning LLMs","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.10988","title":"Back in Style: A Sociolinguistic Approach to Authoring and Measuring Persona Fidelity in User Simulation","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.12445","title":"Caught in the Act: Probes Effectively Detect Sabotage and Catch Unverbalized Deception","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.16717","title":"Where Is the \"Self\" of a Large Language Model? -- From Self-Index to Self-Reference","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.19817","title":"Model vs. User: Whose Values Prevail? Inference-Time Value Alignment in Multi-Turn Conversations","created":"2026-10-14","cited_by_count":0,"area":"alignment"}],"next_cursor":null}