UQLM: A Python Package for Uncertainty Quantification in Large Language Models
Dylan Bouchard, Mohit Singh Chauhan, David Skarbrevik, Ho-Kyeong Ra, Viren Bajaj, Zeya Ahmad
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.
Related Papers
Distributional Reinforcement Learning on Path-dependent Options2025-07-16Mitigating Object Hallucinations via Sentence-Level Early Intervention2025-07-16Interpretable Bayesian Tensor Network Kernel Machines with Automatic Rank and Feature Selection2025-07-15Joint space-time wind field data extrapolation and uncertainty quantification using nonparametric Bayesian dictionary learning2025-07-15A Risk-Aware Adaptive Robust MPC with Learned Uncertainty Quantification2025-07-15From Physics to Foundation Models: A Review of AI-Driven Quantitative Remote Sensing Inversion2025-07-11ByDeWay: Boost Your multimodal LLM with DEpth prompting in a Training-Free Way2025-07-11Uncertainty Quantification for Motor Imagery BCI -- Machine Learning vs. Deep Learning2025-07-10