UQLM工具包用不确定性量化检测大模型幻觉，提升输出可靠性。
UQLM: A Python Package for Uncertainty Quantification in Large Language Models
- 基于先进不确定性量化技术，为大模型生成内容打分
- 输出0到1的置信度分数，识别高风险幻觉输出
- 开箱即用，易集成，适合关注模型安全的应用开发者
幻觉指大语言模型（LLMs）生成虚假或误导性内容，严重影响下游应用的安全性和可信度。我们提出UQLM，一个用于大模型幻觉检测的Python工具包，采用前沿不确定性量化（UQ）技术。该工具包提供一系列基于UQ的评分器，可计算从0到1的响应级置信度分数。本库为基于不确定性的幻觉检测提供即插即用解决方案，可轻松集成以增强大模型输出的可靠性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。