# Leveraging Multilingual Training for Authorship Representation: Enhancing Generalization across Languages and Domains

arXiv: https://arxiv.org/abs/2509.16531 · HTML: https://mlsanity.com/paper/2509.16531/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 51 references that are in the map.
- First posted on arXiv 20 Sep 2025.

## Builds on (most cited first, 26 of 26)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond](https://mlsanity.com/paper/1812.10464/) (2018)
- [LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders](https://mlsanity.com/paper/2404.05961/) (2024)
- [Can contrastive learning avoid shortcut solutions?](https://mlsanity.com/paper/2106.11230/) (2021)
- [Same Author or Just Same Topic? Towards Content-Independent Style Representations](https://mlsanity.com/paper/2204.04907/) (2022)
- [Towards a Common Understanding of Contributing Factors for Cross-Lingual Transfer in Multilingual Language Models: A Review](https://mlsanity.com/paper/2305.16768/) (2023)
- [Few-Shot Detection of Machine-Generated Text using Style Representations](https://mlsanity.com/paper/2401.06712/) (2024)
- [StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examples](https://mlsanity.com/paper/2410.12757/) (2024)
- [Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression](https://mlsanity.com/paper/2305.16536/) (2023)
- [Match the Script, Adapt if Multilingual: Analyzing the Effect of Multilingual Pretraining on Cross-lingual Transferability](https://mlsanity.com/paper/2203.10753/) (2022)
- [Idiosyncratic but not Arbitrary: Learning Idiolects in Online Registers Reveals Distinctive yet Consistent Individual Styles](https://mlsanity.com/paper/2109.03158/) (2021)
- [StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elements](https://mlsanity.com/paper/2408.15666/) (2024)
- [The Topic Confusion Task: A Novel Scenario for Authorship Attribution](https://mlsanity.com/paper/2104.08530/) (2021)
- [Can Authorship Representation Learning Capture Stylistic Features?](https://mlsanity.com/paper/2308.11490/) (2023)
- [TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings](https://mlsanity.com/paper/2406.15586/) (2024)
- [Similarity Learning for Authorship Verification in Social Media](https://mlsanity.com/paper/1908.07844/) (2019)
- [Key ingredients for effective zero-shot cross-lingual knowledge transfer in generative tasks](https://mlsanity.com/paper/2402.12279/) (2024)
- [Authorship Style Transfer with Policy Optimization](https://mlsanity.com/paper/2403.08043/) (2024)
- [Keep It Private: Unsupervised Privatization of Online Text](https://mlsanity.com/paper/2405.10260/) (2024)
- [Separating Style from Substance: Enhancing Cross-Genre Authorship Attribution through Data Selection and Presentation](https://mlsanity.com/paper/2408.05192/) (2024)
- [Latent Space Interpretation for Stylistic Analysis and Explainable Authorship Attribution](https://mlsanity.com/paper/2409.07072/) (2024)
- [IDTraffickers: An Authorship Attribution Dataset to link and connect Potential Human-Trafficking Operations on Text Escort Advertisements](https://mlsanity.com/paper/2310.05484/) (2023)
- [How Good is Your Wikipedia? Auditing Data Quality for Low-resource and Multilingual NLP](https://mlsanity.com/paper/2411.05527/) (2024)

## Built on by (most cited first, 8 of 8)

- [One-shot Style Transfer LLM log-probabilities for Authorship Attribution and Verification](https://mlsanity.com/paper/2510.13302/) (2025)
- [GerAV: Towards New Heights in German Authorship Verification using Fine-Tuned LLMs on a New Benchmark](https://mlsanity.com/paper/2601.13711/) (2026)
- [Can You Make It Sound Like You? Post-Editing LLM-Generated Text for Personal Style](https://mlsanity.com/paper/2604.24444/) (2026)
- [Unsupervised Style Representation Learning for AI-Text Detection via Paraphrase Inversion](https://mlsanity.com/paper/2606.10099/) (2026)
- [STEB: Style Text Embedding Benchmark](https://mlsanity.com/paper/2606.31741/) (2026)
- [Authorship Verification of Transcribed German-Language Videos](https://mlsanity.com/paper/2607.29168/) (2026)
- [When Writing Style Drifts: Benchmarking Authorship Verification under Distribution Shifts in Genre, Time and the AI-Era](https://mlsanity.com/paper/2608.17979/) (2026)
- [Fantastic Metrics and How to Find Them: Meta-Evaluating Metrics for Multi-lingual Style-Personalized Generation](https://mlsanity.com/paper/2610.19166/) (2026)

## Abstract (arXiv)

Authorship representation (AR) learning, which models an author's unique writing style, has demonstrated strong performance in authorship attribution tasks. However, prior research has primarily focused on monolingual settings-mostly in English-leaving the potential benefits of multilingual AR models underexplored. We introduce a novel method for multilingual AR learning that incorporates two key innovations: probabilistic content masking, which encourages the model to focus on stylistically indicative words rather than content-specific words, and language-aware batching, which improves contrastive learning by reducing cross-lingual interference. Our model is trained on over 4.5 million authors across 36 languages and 13 domains. It consistently outperforms monolingual baselines in 21 out of 22 non-English languages, achieving an average Recall@8 improvement of 4.85%, with a maximum gain of 15.91% in a single language. Furthermore, it exhibits stronger cross-lingual and cross-domain generalization compared to a monolingual model trained solely on English. Our analysis confirms the effectiveness of both proposed techniques, highlighting their critical roles in the model's improved performance.