Trust but Verify: Prover-Verifier Deliberation for Selective LLM Prediction 事件

Trust but Verify: Prover-Verifier Deliberation for Selective LLM Prediction arXiv:2605.25133v1 Announce Type: cross Abstract: Reliably knowing when a language model is correct is almost as important as being correct. We introduce prover-verifier deliberation (PVD), an inference-time protocol grounded in interactive proof theory, as a mechanism for selective prediction: the protocol produces both an answer and a structured confidence verdict, allowing a system to report high-confidence answers w