SyntaxShap: Syntax-aware Explainability Method for Text Generation

Understand

To harness the power of large language models in safety-critical domains, we need to ensure the explainability of their predictions.

• However, despite the significant attention to model interpretability, there remains an unexplored domain in explaining sequence-to-sequence tasks using methods tailored for textual data.
• This paper introduces SyntaxShap, a local, model-agnostic explainability method for text generation that takes into consideration the syntax in the text data.
• The presented work extends Shapley values to account for parsing-based syntactic dependencies.