Can LLMs faithfully generate their layperson-understandable 'self'?: A Case Study in High-Stakes Domains
This addresses the critical need for trust and transparency in LLMs for non-experts in high-stakes applications, representing a novel approach rather than an incremental improvement.
The paper tackled the problem of making Large Language Models (LLMs) explainable to laypersons in high-stakes domains like law, health, and finance, and found that their proposed method, ReQuesting, enabled faithful generation of understandable explanations with high reproducibility and alignment with the models' intrinsic reasoning.
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.