{"total":17,"rows":[{"id":"2603.16567","title":"Characterizing Delusional Spirals through Human-LLM Chat Logs","created":"2026-03-17","cited_by_count":23,"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":"2606.30850","title":"BayesBench: Evaluating LLM Belief Trajectories Under Multi-Turn Evidence Accumulation","created":"2026-06-29","cited_by_count":7,"area":null},{"id":"2606.10949","title":"Recalling Too Well: Sycophancy Evaluation and Mitigation in Memory-Augmented Models","created":"2026-06-09","cited_by_count":4,"area":null},{"id":"2604.08525","title":"Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2605.12412","title":"Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2601.05905","title":"Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2604.11609","title":"Intersectional Sycophancy: How Perceived User Demographics Shape False Validation in Large Language Models","created":"2026-04-13","cited_by_count":2,"area":null},{"id":"2606.02776","title":"Topics as Proxies for Sociodemographics: How Conversational Context Affects LLM Answers","created":"2026-06-01","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":"2606.29182","title":"Evidence-Informed LLM Beliefs for Continual Scientific Discovery","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2607.11437","title":"Relational Positioning as a Measurable Risk Object: History-Carried Lock-in and Self-Confabulation in Multi-Turn Human-AI Dialogue","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.05004","title":"DelusionEval: Measuring Delusion-Linked Behaviors in AI Chatbots","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.14692","title":"Identifying Harm in Personalized, Generative AI Systems Requires User-Centered Auditing at the Interaction Level","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.29803","title":"Do LLMs Change Their Minds Like Humans? Diagnosing Human--LLM Divergence in Single-Turn Persuasion Judgments","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.36278","title":"Illusory Truth or Mere Exposure? Model-Dependent Repetition Effects in LLM-Based Social Media Simulations","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.04791","title":"Not All Answers Are Contextually Persuadable: Inference Dynamics in Large Language Models under Contextual Influence","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}