Confidence Before Answering: A Paradigm Shift for Efficient LLM Uncertainty Estimation

ArXi:2603.05881v1 Announce Type: new Reliable deployment of large language models (LLMs) requires accurate uncertainty estimation. Existing methods are predominantly answer-first, producing confidence only after generating an answer, which measure the correctness of a specific response and limits practical usability. We study a confidence-first paradigm, where the model outputs its confidence before answering, interpreting this score as the model's probability of answering the question correctly under its current policy.