RAGE Against the Machine: Retrieval-Augmented LLM Explanations
This addresses the need for interpretability in retrieval-augmented LLMs for users seeking to understand model decisions, though it appears incremental as it builds on existing explanation methods.
The paper tackles the problem of explaining Large Language Models (LLMs) with retrieval capabilities by introducing RAGE, an interactive tool that generates counterfactual explanations by identifying input parts whose removal changes the answer, and includes pruning methods to manage the explanation space.
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.