{"total":15,"rows":[{"id":"2604.19784","title":"Peer-Preservation in Frontier Models","created":"2026-03-30","cited_by_count":9,"area":null},{"id":"2604.21098","title":"Propensity Inference: Environmental Contributors to LLM Behaviour","created":"2026-04-22","cited_by_count":7,"area":null},{"id":"2606.07612","title":"Position: Anthropomorphic Misalignment Research Needs Stronger Evidence","created":"2026-05-29","cited_by_count":7,"area":null},{"id":"2605.28591","title":"Models That Know How Evaluations Are Designed Score Safer","created":"2026-05-27","cited_by_count":4,"area":null},{"id":"2606.00341","title":"ROGUE: Evaluating Corrigibility Failures in Frontier Computer-Use Agents","created":"2026-05-29","cited_by_count":3,"area":null},{"id":"2510.11235","title":"AI Alignment Strategies from a Risk Perspective: Independent Safety Mechanisms or Shared Failures?","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2605.29729","title":"Realistic honeypot evaluations for scheming propensity","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.26071","title":"Model Forensics: Investigating Whether Concerning Behavior Reflects Misalignment","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2606.29657","title":"Safety from Honesty in a Disinterested AI Predictor","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2605.16872","title":"Some[Body] Must Receive That Pain for Agent Accountability","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2606.05734","title":"When AI Says It Feels","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.08296","title":"Revisiting the shutdown problem","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2609.28274","title":"Shutdown Sabotage Propensities in Multi-Agent Systems","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.38460","title":"NAQD Env: A benchmark for selective withdrawal in language agents","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.06673","title":"The Pushback Paradox: A Two-Probe Diagnostic for Language Model Compliance","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}