{"total":16,"rows":[{"id":"2506.19823","title":"Persona Features Control Emergent Misalignment","created":"2025-06-24","cited_by_count":86,"area":null},{"id":"2412.08686","title":"LatentQA: Teaching LLMs to Decode Activations Into Natural Language","created":"2024-12-11","cited_by_count":51,"area":null},{"id":"2507.21919","title":"Training language models to be warm and empathetic makes them less reliable and more sycophantic","created":"2025-07-29","cited_by_count":21,"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":"2604.17031","title":"Where is the Mind? Persona Vectors and LLM Individuation","created":"2026-04-18","cited_by_count":10,"area":null},{"id":"2507.12553","title":"Is This Just Fantasy? Language Model Representations Reflect Human Judgments of Event Plausibility","created":"2025-07-16","cited_by_count":3,"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":"2608.11735","title":"Locating and Controlling Implicit Personalization in Large Language Models","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2601.06599","title":"How Context Shapes Truth: Geometric Transformations of Statement-level Truth Representations in LLMs","created":"2026-01-10","cited_by_count":1,"area":null},{"id":"2601.09141","title":"Identity-Robust Language Model Generation via Content Integrity Preservation","created":"2026-01-14","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":"2606.07631","title":"Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning","created":"2026-05-31","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":"2607.23545","title":"Language Shapes Instruction Hierarchy Compliance in Multilingual LLMs","created":"2026-07-26","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":"2609.12704","title":"Implicit Personality Representations in Humans and LLMs","created":"2026-09-11","cited_by_count":0,"area":null}],"next_cursor":null}