Latent Space Interpretation for Stylistic Analysis and Explainable Authorship Attribution

TL;DR

This paper introduces a method to interpret latent space embeddings in authorship attribution by generating natural language style descriptions, improving model transparency and human performance.

Contribution

It presents a novel approach to interpret latent representations in authorship attribution using representative points and language models for explanations.

Findings

Achieves high prediction agreement with original embeddings

Human evaluation confirms quality of style descriptions

System explanations improve human attribution accuracy by ~20%

Abstract

Recent state-of-the-art authorship attribution methods learn authorship representations of texts in a latent, non-interpretable space, hindering their usability in real-world applications. Our work proposes a novel approach to interpreting these learned embeddings by identifying representative points in the latent space and utilizing LLMs to generate informative natural language descriptions of the writing style of each point. We evaluate the alignment of our interpretable space with the latent one and find that it achieves the best prediction agreement compared to other baselines. Additionally, we conduct a human evaluation to assess the quality of these style descriptions, validating their utility as explanations for the latent space. Finally, we investigate whether human performance on the challenging AA task improves when aided by our system's explanations, finding an average improvement of around +20% in accuracy.