UQLM: A Python Package for Uncertainty Quantification in Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911483247460352 |
|---|---|
| author | Bouchard, Dylan Chauhan, Mohit Singh Skarbrevik, David Ra, Ho-Kyeong Bajaj, Viren Ahmad, Zeya |
| author_facet | Bouchard, Dylan Chauhan, Mohit Singh Skarbrevik, David Ra, Ho-Kyeong Bajaj, Viren Ahmad, Zeya |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_06196 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | UQLM: A Python Package for Uncertainty Quantification in Large Language Models Bouchard, Dylan Chauhan, Mohit Singh Skarbrevik, David Ra, Ho-Kyeong Bajaj, Viren Ahmad, Zeya Computation and Language Artificial Intelligence Machine Learning 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. |
| title | UQLM: A Python Package for Uncertainty Quantification in Large Language Models |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2507.06196 |