AI Threat Alert
Tool MEDIUM relevance
RUBEN: Rule-Based Explanations for Retrieval-Augmented LLM Systems
Joel Rorseth Parke Godfrey Lukasz Golab Divesh Srivastava Jarek Szlichta
Abstract
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.
Metadata
- Comment
- Accepted by ICDE 2026 (Demonstration Track)
Pro Analysis
Full threat analysis, ATLAS technique mapping, compliance impact assessment (ISO 42001, EU AI Act), and actionable recommendations are available with a Pro subscription.
Threat Deep-Dive
ATLAS Mapping
Compliance Reports
Actionable Recommendations