Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Faithful Latent Harm Monitors Work No Better Than the Models Own Behaviour at a Matched False Alarm Rate
Abhishek Mishra, Sagnik Chatterjee, Suyash Maniyar
Large language models have been reported to encode the harmfulness of a request separately from their decision to refuse it, and latent safety monitors such as Latent Guard build o…
cs.AI2026
Measuring Reward Hacking and Reasoning-Answer Decoupling Under Position-Confounded Optimization
Suyash Maniyar, Armaan Sandhu, Abhishek Mishra
When a reward is correct on every training example yet consistent with more than one goal, a model can acquire an unintended one, a failure known as goal misgeneralization. Endpoin…