arXiv AI By Thiago Sandoval, Ufuk Topcu

Regime-Conditional Verification: Correctness Estimation for Adapting and Monitoring Safety Classifiers

Read the original on arXiv AI →

arXiv:2608. 14089v1 Announce Type: new Abstract: Safety classifiers deployed with large language models often fail for two reasons: their decisions reflect the policy learned during training rather than the deployer's desired policy, and their performance degrades as deployment traffic evolves.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

Hugging Face Trending Papers
Jul 13

HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models

Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance. Existing defenses mainly follow two directions: they either intervene during or after fine-tuning through retraining or weight modification, which can be costly and may hurt task performance, or they use model-agnostic safety classifiers, which may miss failures specific to a given fine-tuned checkpoint.