API Is Enough: Conformal Prediction for Large Language Models Without Logit-Access

arXiv:2403.01216v1 Announce Type: cross
Abstract: This study aims to address the pervasive challenge of quantifying uncertainty in large language models (LLMs) without logit-access. Conformal Prediction (CP), known for its model-agnostic and distribution-free features, is a desired approach for various LLMs and data distributions. However, existing CP methods for LLMs typically assume access to the logits, which are unavailable for some API-only LLMs. In addition, logits are known to be miscalibrated, potentially leading to degraded CP performance. To tackle these challenges, …

abstract api arxiv challenge cs.ai cs.cl cs.lg data distribution features free language language models large language large language models llms model-agnostic prediction study type uncertainty