Search papers, labs, and topics across Lattice.
This paper introduces Virgil, an interactive system designed to streamline the navigation of explainability tools for transformer-based language models. The need for such a system arises from the increasing complexity and fragmentation of existing explainability resources, which can hinder effective application in high-stakes environments. Key findings indicate that Virgil significantly enhances user accessibility and tool comparison, facilitating better-informed decisions in the deployment of explainability solutions.
Navigating the fragmented landscape of explainability tools just got easier with Virgil, a system that empowers both experts and non-experts alike.
Explainability for transformer-based language models is becoming crucial as these systems are deployed in high-stakes applications. As a result, the ecosystem of explainability tools is rapidly evolving, becoming richer, but also more fragmented and harder to navigate. To address this challenge, we present Virgil, an interactive system that lets practitioners and researchers, including non-experts, navigate explainability tools for transformer language models. Supported by a curated knowledge base, the system enables users to discover and compare explainability tools within a unified interface.
