3 papers
cs.CL2026
RUBEN: Rule-Based Explanations for Retrieval-Augmented LLM Systems
Joel Rorseth, Parke Godfrey, Lukasz Golab +2
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 applicati…
cs.CL2026
Rule-Based Explanations for Retrieval-Augmented LLM Systems
Joel Rorseth, Parke Godfrey, Lukasz Golab +2
If-then rules are widely used to explain machine learning models; e.g., "if employed = no, then loan application = rejected." We present the first proposal to apply rules to explai…
cs.CL2024
RAGE Against the Machine: Retrieval-Augmented LLM Explanations
Joel Rorseth, Parke Godfrey, Lukasz Golab +2
This paper demonstrates RAGE, an interactive tool for explaining Large Language Models (LLMs) augmented with retrieval capabilities; i.e., able to query external sources and pull r…