Can LLMs faithfully generate their layperson-understandable 'self'?: A Case Study in High-Stakes Domains

TL;DR

This paper introduces a new approach called ReQuesting to evaluate how faithfully large language models can generate explanations understandable by laypersons in high-stakes domains like law, health, and finance.

Contribution

It proposes a novel notion of LLM explainability called ReQuesting and demonstrates its effectiveness across multiple high-stakes domains and models.

Findings

ReQuesting produces faithful, layperson-understandable explanations.

High reproducibility of generated explanations across tasks.

Alignment observed between explanations and LLMs' intrinsic reasoning.

Abstract

Large Language Models (LLMs) have significantly impacted nearly every domain of human knowledge. However, the explainability of these models esp. to laypersons, which are crucial for instilling trust, have been examined through various skeptical lenses. In this paper, we introduce a novel notion of LLM explainability to laypersons, termed $\textit{ReQuesting}$, across three high-priority application domains -- law, health and finance, using multiple state-of-the-art LLMs. The proposed notion exhibits faithful generation of explainable layman-understandable algorithms on multiple tasks through high degree of reproducibility. Furthermore, we observe a notable alignment of the explainable algorithms with intrinsic reasoning of the LLMs.