arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.06703cs.CLcs.AIcs.LG
收藏

可解释交叉质询技术(ICE-T):利用高信息量特征提升 LLM 性能

Interpretable Cross-Examination Technique (ICE-T): Using highly informative features to boost LLM performance

InferLink Corporation(英孚林克公司)

Goran Muric, Ben Delay, Steven Minton

AI总结:

提出 ICE-T 多提示交叉质询框架,将 LLM 响应转为数值特征并交由传统分类器,在医疗、法律数据上提升分类性能与可解释性。

摘要:

本文提出 Interpretable Cross-Examination Technique(ICE-T,可解释交叉质询技术),这是一种新颖方法,通过将结构化多提示技术与大型语言模型(LLM)结合使用,改进零样本和少样本方法的分类性能。在医学和法律等可解释性至关重要的领域,标准模型常因其“黑箱”特性而表现不足。ICE-T 通过使用一系列生成的提示来解决这些局限,使 LLM 能够从多个方向处理问题。随后,LLM 的响应被转换为数值特征向量,并由传统分类器处理。该方法不仅保持高度可解释性,还能让规模较小、能力较弱的模型在零样本条件下达到或超过规模更大、更先进模型的性能。我们在包括病历和法律文书在内的多种数据源上证明了 ICE-T 的有效性;在 F1 分数等分类指标上,该方法始终优于零样本基线。结果表明,ICE-T 可用于在复杂决策环境中同时提升 AI 应用的性能和透明度。

英文摘要:

In this paper, we introduce the Interpretable Cross-Examination Technique (ICE-T), a novel approach that leverages structured multi-prompt techniques with Large Language Models (LLMs) to improve classification performance over zero-shot and few-shot methods. In domains where interpretability is crucial, such as medicine and law, standard models often fall short due to their "black-box" nature. ICE-T addresses these limitations by using a series of generated prompts that allow an LLM to approach the problem from multiple directions. The responses from the LLM are then converted into numerical feature vectors and processed by a traditional classifier. This method not only maintains high interpretability but also allows for smaller, less capable models to achieve or exceed the performance of larger, more advanced models under zero-shot conditions. We demonstrate the effectiveness of ICE-T across a diverse set of data sources, including medical records and legal documents, consistently surpassing the zero-shot baseline in terms of classification metrics such as F1 scores. Our results indicate that ICE-T can be used for improving both the performance and transparency of AI applications in complex decision-making environments.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑