{"total":49,"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":"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":"2601.20834","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":"2605.13329","title":"Tracing Persona Vectors Through LLM Pretraining","created":"2026-05-13","cited_by_count":7,"area":null},{"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":"2604.13076","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":"2607.07916","title":"Persona Cartography: Charting Language Model Personality Traits in Weight Space","created":"2026-07-08","cited_by_count":4,"area":null},{"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":"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":"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":"2607.28818","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":"2602.11358","title":"When Models Examine Themselves: Vocabulary-Activation Correspondence in Self-Referential Processing","created":"2026-02-11","cited_by_count":1,"area":null},{"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":"2606.15420","title":"Constitutional Value Potentials: reading and steering internal priority margins in language models","created":"2026-06-13","cited_by_count":1,"area":null},{"id":"2607.03640","title":"Revealing Hidden Model Behaviors with Task-Specific Self-Reports","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2608.13482","title":"Synthetic Persona Pretraining: Alignment from Token Zero","created":"2026-08-13","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":"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":"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":"2605.20382","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":"2605.28969","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":"2607.13162","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":"2608.03044","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":"2608.20344","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":"2609.00608","title":"Investigating Assistant Bias in LLM User Simulators Using a Role Vector","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.06851","title":"You Are What You Read: Misalignment via In-Context Persona Induction","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.10883","title":"Story Imprinting: AI Assistants Absorb Traits from Human Characters They Resemble","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.22607","title":"Pretrained Persona Mixture Models and Tandem Models for Human Simulation","created":"2026-09-18","cited_by_count":0,"area":null},{"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":"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":"2610.16717","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}],"next_cursor":null}