Interpretable Cross-Examination Technique (ICE-T): Using highly informative features to boost LLM performance
It addresses the need for interpretable AI in critical decision-making fields, offering an incremental improvement over existing methods.
The paper tackles the problem of low interpretability and performance of standard models in domains like medicine and law by introducing ICE-T, a method that uses multi-prompt techniques with LLMs to boost classification, achieving results that surpass zero-shot baselines in metrics like F1 scores.
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.