XAM: Interactive Explainability for Authorship Attribution Models

Milad Alshomary, Anisha Bhatnagar, Peter Zeng, Smaranda Muresan, Owen Rambow +1 more
12/7/2025
cs.CL

No confident code implementation found for this paper.

Abstract

We present IXAM, an Interactive eXplainability framework for Authorship Attribution Models. Given an authorship attribution (AA) task and an embedding-based AA model, our tool enables users to interactively explore the model's embedding space and construct an explanation of the model's prediction as a set of writing style features at different levels of granularity. Through a user evaluation, we demonstrate the value of our framework compared to predefined stylistic explanations.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

ALMs: Authorial Language Models for Authorship Attribution

83% match2024

CAVE: Controllable Authorship Verification Explanations

83% match1 repo32024

Latent Space Interpretation for Stylistic Analysis and Explainable Authorship Attribution

82% match2024

Can Large Language Models Identify Authorship?

81% match1 repo132024

LumiXAI: A Modular Full-Stack Framework for Feature Attribution

80% match2026

Learning Text Styles: A Study on Transfer, Attribution, and Verification

80% match2025

Cite this paper

@article{alshomary2025xam,
  title  = {XAM: Interactive Explainability for Authorship Attribution Models},
  author = {Milad Alshomary and Anisha Bhatnagar and Peter Zeng and Smaranda Muresan and Owen Rambow and Kathleen McKeown},
  year   = {2025},
  eprint = {2512.06924},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2512.06924v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2512.06924.svg)](https://codeofpaper.com/paper/2512.06924)

Discussion