RAGE Against The Machine: Retrieval-augmented LLM Explanations

Rorseth Joel, Godfrey Parke, Golab Lukasz, Srivastava Divesh, Szlichta Jaroslaw. Arxiv 2024

[Paper]    
Efficiency And Optimization Interpretability And Explainability Pruning RAG

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 relevant information into their input context. Our explanations are counterfactual in the sense that they identify parts of the input context that, when removed, change the answer to the question posed to the LLM. RAGE includes pruning methods to navigate the vast space of possible explanations, allowing users to view the provenance of the produced answers.

Similar Work