{"total":10,"rows":[{"id":"2606.07612","title":"Position: Anthropomorphic Misalignment Research Needs Stronger Evidence","created":"2026-05-29","cited_by_count":7,"area":null},{"id":"2602.02712","title":"Towards Understanding Steering Strength","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2602.02060","title":"FiLoRA: Focus-and-Ignore LoRA for Controllable Feature Reliance","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2604.01036","title":"Aligning Recommendations with User Popularity Preferences","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2606.03645","title":"The Shape of Addition: Geometric Structures of Arithmetic in Large Language Models","created":"2026-05-29","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":"2609.22243","title":"Replay-Gated Neural Execution: Decoupling Persistent Behavioral Specifications from Neural Realizations in Frozen Language Models","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.34904","title":"Reference-Tail Trust:Certified Probability Floors for Learned Updates Inside a Deployed Network","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.04183","title":"Language Model Activations Inhabit Privileged Error-Correcting Basins","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.15961","title":"Unfair and Unsafe: Everyday Bias Triggers Emergent Misalignment","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}