{"total":30,"rows":[{"id":"2506.19823","title":"Persona Features Control Emergent Misalignment","created":"2025-06-24","cited_by_count":86,"area":null},{"id":"2410.11905","title":"A Scalable Communication Protocol for Networks of Large Language Models","created":"2024-10-14","cited_by_count":45,"area":null},{"id":"2502.12964","title":"Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer","created":"2025-02-18","cited_by_count":27,"area":null},{"id":"2406.13261","title":"BeHonest: Benchmarking Honesty in Large Language Models","created":"2024-06-19","cited_by_count":24,"area":null},{"id":"2406.19354","title":"Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs?","created":"2024-06-27","cited_by_count":24,"area":null},{"id":"2407.08582","title":"On the Universal Truthfulness Hyperplane Inside LLMs","created":"2024-07-11","cited_by_count":24,"area":null},{"id":"2505.16467","title":"Reading Between the Prompts: How Stereotypes Shape LLM's Implicit Personalization","created":"2025-05-22","cited_by_count":24,"area":null},{"id":"2407.12858","title":"Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)","created":"2024-07-10","cited_by_count":20,"area":null},{"id":"2404.09971","title":"Constructing Benchmarks and Interventions for Combating Hallucinations in LLMs","created":"2024-04-15","cited_by_count":19,"area":null},{"id":"2406.11096","title":"The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models","created":"2024-06-16","cited_by_count":19,"area":null},{"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":"2402.06625","title":"Understanding the Effects of Iterative Prompting on Truthfulness","created":"2024-02-09","cited_by_count":14,"area":null},{"id":"2410.22071","title":"Distinguishing Ignorance from Error in LLM Hallucinations","created":"2024-10-29","cited_by_count":14,"area":null},{"id":"2407.06908","title":"Divine LLaMAs: Bias, Stereotypes, Stigmatization, and Emotion Representation of Religion in Large Language Models","created":"2024-07-09","cited_by_count":12,"area":null},{"id":"2510.15804","title":"Emergence of Linear Truth Encodings in Language Models","created":"2025-10-17","cited_by_count":12,"area":null},{"id":"2411.02989","title":"Growing a Tail: Increasing Output Diversity in Large Language Models","created":"2024-11-05","cited_by_count":9,"area":null},{"id":"2401.12292","title":"GRATH: Gradual Self-Truthifying for Large Language Models","created":"2024-01-22","cited_by_count":6,"area":null},{"id":"2503.01030","title":"Language Models Predict Empathy Gaps Between Social In-groups and Out-groups","created":"2025-03-02","cited_by_count":6,"area":null},{"id":"2505.00003","title":"A Review of Incorporating Psychological Theories in LLMs","created":"2025-03-28","cited_by_count":6,"area":null},{"id":"2510.24222","title":"HACK: Hallucinations Along Certainty and Knowledge Axes","created":"2025-10-28","cited_by_count":6,"area":null},{"id":"2312.03853","title":"Dr. Jekyll and Mr. Hyde: Two Faces of LLMs","created":"2023-12-06","cited_by_count":3,"area":null},{"id":"2505.23410","title":"From Parameters to Prompts: Understanding and Mitigating the Factuality Gap between Fine-Tuned LLMs","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2506.08593","title":"Hateful Person or Hateful Model? Investigating the Role of Personas in Hate Speech Detection by Large Language Models","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2603.11749","title":"Truth as a Compression Artifact in Language Model Training","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2607.01690","title":"Epistemic Goggles: A Pretrained Module that Induces an Epistemic Frame via Gradient Editing","created":"2026-07-02","cited_by_count":1,"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":"2607.18804","title":"Elicitation without Backpropagation: Steering Model Behavior by Optimizing the Latent Posterior","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2609.04485","title":"Cultural Misalignment in Large Language Models: Detection, Measurement, and Mitigation Through Targeted Fine-Tuning","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.11109","title":"How AI Coders Discuss, Disagree, and Reach Consensus: Challenges and Opportunities for LLM-Based Qualitative Coding","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2610.04676","title":"Extracting Persona Subspaces Through Iterative Nullspace Projection For Modulation","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}