Layered Insights: Generalizable Analysis of Human Authorial Style by Leveraging All Transformer Layers

ACL ARR 2025 May Submission1068 Authors

Abstract: We propose a new approach for the authorship attribution task that leverages the various linguistic representations learned at different layers of pre-trained transformer-based models. We evaluate our approach on two popular authorship attribution models and three evaluation datasets, in in-domain and out-of-domain scenarios. We found that utilizing various transformer layers improves the robustness of authorship attribution models when tested on out-of-domain data, resulting in new state-of-the-art results. Our analysis gives further insights into how our model's different layers get specialized in representing certain stylistic features that benefit the model when tested out of the domain.

Paper Type: Long

Research Area: Sentiment Analysis, Stylistic Analysis, and Argument Mining

Research Area Keywords: authorship attribution, writing style

Contribution Types: Model analysis & interpretability, Publicly available software and/or pre-trained models

Languages Studied: English

Submission Number: 1068