arXiv:2512.19027v1 Announce Type: new
Abstract: Developers often struggle to specify correct training labels and rewards. Perhaps they don’t need to. We propose recontextualization, which reduces how often language models “game” training signals, performing misbehaviors those signals mistakenly reinforce. We show recontextualization prevents models from learning to 1) prioritize evaluation metrics over chat response quality; 2) special-case code to pass incorrect tests; 3) lie to users; and 4) become sycophantic. Our method works by generating completions from prompts discouraging misbehavior and then recontextualizing them as though they were in response to prompts permitting misbehavior. Recontextualization trains language models to resist misbehavior even when instructions permit it. This mitigates the reinforcement of misbehavior from misspecified training signals, reducing specification gaming without improving the supervision signal.
Just-In-Time Adaptive Interventions for Weight Management Among Adults With Excess Body Weight: Scoping Review
Background: Just-in-time adaptive interventions (JITAIs) use real-time monitoring to deliver personalized support at optimal moments, demonstrating potential for improving lifestyle behaviors in weight management. Objective: