XAM: Interactive Explainability for Authorship Attribution Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Alshomary, Milad, Bhatnagar, Anisha, Zeng, Peter, Muresan, Smaranda, Rambow, Owen, McKeown, Kathleen
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917131905400832
author Alshomary, Milad
Bhatnagar, Anisha
Zeng, Peter
Muresan, Smaranda
Rambow, Owen
McKeown, Kathleen
author_facet Alshomary, Milad
Bhatnagar, Anisha
Zeng, Peter
Muresan, Smaranda
Rambow, Owen
McKeown, Kathleen
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_06924
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle XAM: Interactive Explainability for Authorship Attribution Models
Alshomary, Milad
Bhatnagar, Anisha
Zeng, Peter
Muresan, Smaranda
Rambow, Owen
McKeown, Kathleen
Computation and Language
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.
title XAM: Interactive Explainability for Authorship Attribution Models
topic Computation and Language
url https://arxiv.org/abs/2512.06924