New tool RUBEN generates rule-based explanations for retrieval-augmented LLMs

By PulseAugur Editorial · Summary by gemini-2.5-flash-lite from 1 source

Researchers have developed RUBEN, a new tool designed to generate rule-based explanations for retrieval-augmented large language models. This system uses pruning strategies to identify a minimal set of rules that effectively explain the model's outputs. The paper also highlights RUBEN's utility in enhancing LLM safety by testing the robustness of safety training and the impact of adversarial prompts. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Provides a method for understanding and potentially improving the safety and reliability of retrieval-augmented LLM systems.

RANK_REASON The cluster contains an academic paper detailing a new method for explaining LLM behavior. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

RUBEN
LLM

paper
safety

COVERAGE [1]

arXiv cs.CL TIER_1 · Jarek Szlichta · 2026-05-11 17:10

RUBEN: Rule-Based Explanations for Retrieval-Augmented LLM Systems

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 subsum…

COVERAGE [1]

RUBEN: Rule-Based Explanations for Retrieval-Augmented LLM Systems

RELATED ENTITIES

RELATED TOPICS