In this paper, we introduce GhostWriteBench, a dataset for LLM authorship attribution. It comprises long-form texts (50K+ words per book) generated by frontier LLMs, and is designed to test generalisation across multiple out-of-distribution (OOD) dimensions, including domain and unseen LLM author. We also propose TRACE -- a novel fingerprinting method that is interpretable and lightweight -- that works for both open- and closed-source models. TRACE creates the fingerprint by capturing token-level transition patterns (e.g., word rank) estimated by another lightweight language model. Experiments on GhostWriteBench demonstrate that TRACE achieves state-of-the-art performance, remains robust in OOD settings, and works well in limited training data scenarios.
Cite
@article{arxiv.2603.28054,
title = {Who Wrote the Book? Detecting and Attributing LLM Ghostwriters},
author = {Anudeex Shetty and Qiongkai Xu and Olga Ohrimenko and Jey Han Lau},
journal= {arXiv preprint arXiv:2603.28054},
year = {2026}
}