1
Trust but Verify: Prover-Verifier Deliberation for Selective LLM Prediction
基于交互式证明理论，让大模型通过“证明者-验证者”相互校验，实现有选择地预测——知道何时该回答、何时该存疑。
arXiv:2605.25133v1 Announce Type: new Abstract: Reliably knowing when a language model is correct is almost as important as being correct. We introduc…