This paper demonstrates RUBEN, an interactive tool for discovering minimal rules to explain the outputs of retrieval-augmented large language models (LLMs) in data-driven applications. We leverage novel pruning strategies to efficiently identify a minimal set of rules that subsume all others. We further demonstrate novel applications of these rules for LLM safety, specifically to test the resiliency of safety training and effectiveness of adversarial prompt injections.
@article{arxiv.2605.10862,
title = {RUBEN: Rule-Based Explanations for Retrieval-Augmented LLM Systems},
author = {Joel Rorseth and Parke Godfrey and Lukasz Golab and Divesh Srivastava and Jarek Szlichta},
journal= {arXiv preprint arXiv:2605.10862},
year = {2026}
}