Query-Level Uncertainty in Large Language Models

TL;DR

This paper introduces a training-free method called Internal Confidence to detect when large language models are uncertain about a query, enabling more efficient and trustworthy adaptive inference without additional training.

Contribution

Proposes a novel, training-free uncertainty estimation method for LLMs that improves confidence accuracy and reduces inference costs in adaptive settings.

Findings

Internal Confidence outperforms baselines in confidence quality

Reduces inference costs in retrieval-augmented and cascading models

Maintains performance while improving efficiency

Abstract

It is important for Large Language Models (LLMs) to be aware of the boundary of their knowledge, distinguishing queries they can confidently answer from those that lie beyond their capabilities. Such awareness enables models to perform adaptive inference, such as invoking retrieval-augmented generation (RAG), engaging in slow and deep thinking, or abstaining from answering when appropriate. These mechanisms are key to developing efficient and trustworthy AI. In this work, we propose a method to detect knowledge boundaries via Query-Level Uncertainty, which estimates if a model is capable of answering a given query before generating any tokens, thus avoiding the generation cost. To this end, we propose a novel, training-free method called Internal Confidence, which leverages self-evaluations across layers and tokens to provide a reliable signal of uncertainty. Empirical studies on both factual question answering and mathematical reasoning tasks demonstrate that our Internal Confidence outperforms several baselines in quality of confidence while being computationally cheaper. Furthermore, we demonstrate its benefits in adaptive inference settings, showing that for RAG and model cascading it reduces inference costs while preserving overall performance.