Semantic Token Clustering for Efficient Uncertainty Quantification in Large Language Models

2026-03-20

AI Summary

This work addresses the challenge of unreliable outputs from large language models and the high computational cost of existing uncertainty quantification methods. To this end, the authors propose an efficient approach that leverages semantic information from internal token embeddings for clustering. By integrating prefix matching with aggregated probability mass over semantic clusters, the method achieves accurate uncertainty estimation with only a single model pass and without requiring any auxiliary models. Evaluated across multiple benchmarks, the proposed technique matches the performance of state-of-the-art uncertainty quantification methods while significantly reducing computational overhead, thereby offering a practical balance between efficiency and accuracy.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Uncertainty Representations
• Natural Language Processing: (Large) Language Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Large language models for search
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• uncertainty quantification
• large language models
• computational overhead
• overconfidence
• reliability

Innovation

• Semantic Token Clustering
• Uncertainty Quantification
• Large Language Models
• Efficient Inference
• Embedding Clustering