Research
Virgil: Navigating Explainability for Transformer-based Language Models
arXiv:2608.25555v1 Announce Type: new Abstract: Explainability for transformer-based language models is becoming crucial as these systems are deployed in high-stakes applications. As a result, the eco
arXiv:2608.25555v1 Announce Type: new Abstract: 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.
Related
- Dual Path Attribution: Efficient Attribution for SwiGLU-Transformers through Layer-Wise Target Propagation
- EVADE: LLM-Based Explanation Generation and Validation for Error Detection in NLI
- Model Internal Sleuthing: Finding Lexical Identity and Inflectional Features in Modern Language Models
- Attribution, Citation, and Quotation: A Survey of Evidence-based Text Generation with Large Language Models
Source: arXiv cs.CL | 2026-08-27