# Explainable Disentangled Representation Learning for Generalizable Authorship Attribution in the Era of Generative AI

arXiv: https://arxiv.org/abs/2604.21300 · HTML: https://mlsanity.com/paper/2604.21300/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 36 references that are in the map.
- First posted on arXiv 23 Apr 2026.

## Builds on (most cited first, 19 of 19)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [Defending Against Neural Fake News](https://mlsanity.com/paper/1905.12616/) (2019)
- [LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders](https://mlsanity.com/paper/2404.05961/) (2024)
- [Generative Representational Instruction Tuning](https://mlsanity.com/paper/2402.09906/) (2024)
- [Same Author or Just Same Topic? Towards Content-Independent Style Representations](https://mlsanity.com/paper/2204.04907/) (2022)
- [Fine-Grained Spoiler Detection from Large-Scale Review Corpora](https://mlsanity.com/paper/1905.13416/) (2019)
- [Few-Shot Detection of Machine-Generated Text using Style Representations](https://mlsanity.com/paper/2401.06712/) (2024)
- [Explainable Authorship Verification in Social Media via Attention-based Similarity Learning](https://mlsanity.com/paper/1910.08144/) (2019)
- [The Topic Confusion Task: A Novel Scenario for Authorship Attribution](https://mlsanity.com/paper/2104.08530/) (2021)
- [Whodunit? Learning to Contrast for Authorship Attribution](https://mlsanity.com/paper/2209.11887/) (2022)
- [Information-theoretic regularization for Multi-source Domain Adaptation](https://mlsanity.com/paper/2104.01568/) (2021)
- [So Different Yet So Alike! Constrained Unsupervised Text Style Transfer](https://mlsanity.com/paper/2205.04093/) (2022)
- [Learning Multilingual Sentence Representations with Cross-lingual Consistency Regularization](https://mlsanity.com/paper/2306.06919/) (2023)
- [ULLME: A Unified Framework for Large Language Model Embeddings with Generation-Augmented Learning](https://mlsanity.com/paper/2408.03402/) (2024)
- [Beyond Contrastive Learning: A Variational Generative Model for Multilingual Retrieval](https://mlsanity.com/paper/2212.10726/) (2022)

## Built on by (most cited first, 1 of 1)

- [Back in Style: A Sociolinguistic Approach to Authoring and Measuring Persona Fidelity in User Simulation](https://mlsanity.com/paper/2610.10988/) (2026)

## Abstract (arXiv)

Learning robust representations of authorial style is crucial for authorship attribution and AI-generated text detection. However, existing methods often struggle with content-style entanglement, where models learn spurious correlations between authors' writing styles and topics, leading to poor generalization across domains. To address this challenge, we propose Explainable Authorship Variational Autoencoder (EAVAE), a novel framework that explicitly disentangles style from content through architectural separation-by-design. EAVAE first pretrains style encoders using supervised contrastive learning on diverse authorship data, then finetunes with a Variational Autoencoder (VEA) architecture using separate encoders for style and content representations. Disentanglement is enforced through a novel discriminator that not only distinguishes whether pairs of style/content representations belong to the same or different authors/content sources, but also generates natural language explanation for their decision, simultaneously mitigating confounding information and enhancing interpretability. Extensive experiments demonstrate the effectiveness of EAVAE. On authorship attribution, we achieve state-of-the-art performance on various datasets, including Amazon Reviews, PAN21, and HRS. For AI-generated text detection, EAVAE excels in few-shot learning over the M4 dataset. Code and data repositories are available onlinefootnotehttps://github.com/hieum98/avae footnotehttps://huggingface.co/collections/Hieuman/document-level-authorship-datasets.