Semantic Token Clustering for Efficient Uncertainty Quantification in Large Language Models

TL;DR

This paper introduces Semantic Token Clustering (STC), an efficient method for uncertainty quantification in large language models that reduces computational costs by leveraging semantic token groupings without auxiliary models.

Contribution

We propose STC, a novel semantic clustering approach that enables reliable uncertainty estimation in LLMs with minimal computational overhead and no need for repeated sampling.

Findings

STC achieves comparable accuracy to state-of-the-art methods.

STC significantly reduces computational overhead.

STC requires only a single model generation.

Abstract

Large language models (LLMs) have demonstrated remarkable capabilities across diverse tasks. However, the truthfulness of their outputs is not guaranteed, and their tendency toward overconfidence further limits reliability. Uncertainty quantification offers a promising way to identify potentially unreliable outputs, but most existing methods rely on repeated sampling or auxiliary models, introducing substantial computational overhead. To address these limitations, we propose Semantic Token Clustering (STC), an efficient uncertainty quantification method that leverages the semantic information inherently encoded in LLMs. Specifically, we group tokens into semantically consistent clusters using embedding clustering and prefix matching, and quantify uncertainty based on the probability mass aggregated over the corresponding semantic cluster. Our approach requires only a single generation and does not depend on auxiliary models. Experimental results show that STC achieves performance comparable to state-of-the-art baselines while substantially reducing computational overhead.