Value Probes: Learned Value Functions for Beam-Search Red Teaming
arXiv:2610.38526v1 Announce Type: new Abstract: Automated red-team auditing of language models is an important way to evaluate safety-relevant behaviors. These audits implicitly search a tree of possible conversation pathways: at each turn an auditor model decides which conversation to continue, and an LLM judge scores the dialogue. We emphasize that this auditing procedure is a Markov decision process, where states are the conversation history, actions are candidate responses, and rewards are…