UQLM: A Python Package for Uncertainty Quantification in Large Language Models

Dylan Bouchard, Mohit Singh Chauhan, David Skarbrevik, Ho-Kyeong Ra, Viren Bajaj +1 more
7/8/2025
cs.CLcs.AIcs.LG

No official code found. Best implementation: cvs-health/uqlm (1,210 stars, Apache-2.0, last commit 2026-04-28).

Abstract

Hallucinations, defined as instances where Large Language Models (LLMs) generate false or misleading content, pose a significant challenge that impacts the safety and trust of downstream applications. We introduce UQLM, a Python package for LLM hallucination detection using state-of-the-art uncertainty quantification (UQ) techniques. This toolkit offers a suite of UQ-based scorers that compute response-level confidence scores ranging from 0 to 1. This library provides an off-the-shelf solution for UQ-based hallucination detection that can be easily integrated to enhance the reliability of LLM outputs.

View on arXivView PDF

Code Implementations(1)

cvs-health/uqlmCommunity100%
Apache-2.0

UQLM: Uncertainty Quantification for Language Models, is a Python package for UQ-based LLM hallucination detection

1,210135PythonApr 17, 20255 months agoApache-2.0
ai-evaluationai-safetyconfidence-estimationconfidence-scorehallucination+9 more

Similar Papers

Uncertainty Quantification for Language Models: A Suite of Black-Box, White-Box, LLM Judge, and Ensemble Scorers

94% match1 repo1.2k2025

Uncertainty Quantification for Hallucination Detection in Large Language Models: Foundations, Methodology, and Future Directions

91% match2025

A Head to Predict and a Head to Question: Pre-trained Uncertainty Quantification Heads for Hallucination Detection in LLM Outputs

90% match2025

Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study

89% match2026

Mathematical Analysis of Hallucination Dynamics in Large Language Models: Uncertainty Quantification, Advanced Decoding, and Principled Mitigation

87% match2025

Cost-Effective Hallucination Detection for LLMs

87% match2024

Cite this paper

@article{bouchard2025uqlm,
  title  = {UQLM: A Python Package for Uncertainty Quantification in Large Language Models},
  author = {Dylan Bouchard and Mohit Singh Chauhan and David Skarbrevik and Ho-Kyeong Ra and Viren Bajaj and Zeya Ahmad},
  year   = {2025},
  eprint = {2507.06196},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2507.06196v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2507.06196.svg)](https://codeofpaper.com/paper/2507.06196)

Discussion