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

TL;DR

ICE-T is a novel interpretable approach that uses structured multi-prompt techniques with LLMs to enhance classification performance while maintaining transparency, especially in sensitive domains like medicine and law.

Contribution

ICE-T introduces a multi-prompt structured method that transforms LLM responses into features for traditional classifiers, improving performance and interpretability in zero-shot settings.

Findings

Outperforms zero-shot baselines in classification metrics

Maintains high interpretability in sensitive domains

Achieves comparable or better results with smaller models

Abstract

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.