{"total":14,"rows":[{"id":"2512.08093","title":"Training LLMs for Honesty via Confessions","created":"2025-12-08","cited_by_count":22,"area":null},{"id":"2507.19218","title":"Technological folie \\`a deux: Feedback Loops Between AI Chatbots and Mental Illness","created":"2025-07-25","cited_by_count":15,"area":null},{"id":"2511.22662","title":"Difficulties with Evaluating a Deception Detector for AIs","created":"2025-11-27","cited_by_count":13,"area":null},{"id":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"id":"2512.00742","title":"On the Regulatory Potential of User Interfaces for AI Agent Governance","created":"2025-11-30","cited_by_count":3,"area":null},{"id":"2604.27865","title":"KellyBench: A Benchmark for Long-Horizon Sequential Decision Making","created":"2026-04-30","cited_by_count":3,"area":null},{"id":"2607.14345","title":"Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values","created":"2026-07-15","cited_by_count":3,"area":null},{"id":"2608.23875","title":"AI Finds A Way","created":"2026-08-24","cited_by_count":3,"area":null},{"id":"2602.05164","title":"Position: Capability Control Should be a Separate Goal From Alignment","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2512.08645","title":"Chain-of-Image Generation: Toward Monitorable and Controllable Image Generation","created":"2025-12-09","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":"2608.21664","title":"Measuring Activation Control in Large Language Models","created":"2026-08-21","cited_by_count":1,"area":null},{"id":"2602.17676","title":"Epistemic Traps: Rational Misalignment Driven by Model Misspecification","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2608.16213","title":"Process-Constituted Intelligence: A Shared Criterion for Humans and Machines","created":"2026-08-17","cited_by_count":0,"area":null}],"next_cursor":null}