用单块显卡训练出能快速检测大模型幻觉的高效集成模型。
Hallucination Detection in LLMs: Fast and Memory-Efficient Fine-Tuned Models
- 基于不确定性估计，设计轻量级微调方法构建大模型集成
- 仅需单卡即可完成训练与推理，内存占用极低
- 适合医疗、自动驾驶等高风险场景的幻觉检测应用
在自动驾驶、医疗、保险等高风险场景中，不确定性估计是部署AI的必要条件。近年来大型语言模型（LLMs）广泛应用，但其易产生幻觉，可能带来严重后果。尽管表现优异，现有模型训练和运行成本高昂，需要大量计算与内存，导致实际中难以使用集成方法。本文提出一种新方法，可实现大模型集成的快速、低内存微调。结果表明，所生成的集成模型具备幻觉检测能力，且在实践中可行——训练与推理仅需一块GPU，显著降低资源门槛。
原文摘要 · Abstract (English)
Uncertainty estimation is a necessary component when implementing AI in high-risk settings, such as autonomous cars, medicine, or insurances. Large Language Models (LLMs) have seen a surge in popularity in recent years, but they are subject to hallucinations, which may cause serious harm in high-risk settings. Despite their success, LLMs are expensive to train and run: they need a large amount of computations and memory, preventing the use of ensembling methods in practice. In this work, we present a novel method that allows for fast and memory-friendly training of LLM ensembles. We show that the resulting ensembles can detect hallucinations and are a viable approach in practice as only one GPU is needed for training and inference.
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。