Salvato in:
Dettagli Bibliografici
Autori principali: Rorseth, Joel, Godfrey, Parke, Golab, Lukasz, Srivastava, Divesh, Szlichta, Jarek
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2605.10862
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910209521221632
author Rorseth, Joel
Godfrey, Parke
Golab, Lukasz
Srivastava, Divesh
Szlichta, Jarek
author_facet Rorseth, Joel
Godfrey, Parke
Golab, Lukasz
Srivastava, Divesh
Szlichta, Jarek
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_10862
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RUBEN: Rule-Based Explanations for Retrieval-Augmented LLM Systems
Rorseth, Joel
Godfrey, Parke
Golab, Lukasz
Srivastava, Divesh
Szlichta, Jarek
Computation and Language
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.
title RUBEN: Rule-Based Explanations for Retrieval-Augmented LLM Systems
topic Computation and Language
url https://arxiv.org/abs/2605.10862