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

2025/09/20 by Junghwan Kim, Haotian Zhang, Kim, Junghwan +3
Computer Science · #Authorship Attribution and Profiling #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2509.16531

openalex publication_date 2025/09/20 · openalex created_date 2025/10/16 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• How Good is Your Wikipedia? Auditing Data Quality for Low-resource and Multilingual NLP
• StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examples
• Latent Space Interpretation for Stylistic Analysis and Explainable Authorship Attribution
• StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elements
• Separating Style from Substance: Enhancing Cross-Genre Authorship Attribution through Data Selection and Presentation
• TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings
• Keep It Private: Unsupervised Privatization of Online Text
• LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
• Authorship Style Transfer with Policy Optimization
• Key ingredients for effective zero-shot cross-lingual knowledge transfer in generative tasks
• Few-Shot Detection of Machine-Generated Text using Style Representations
• IDTraffickers: An Authorship Attribution Dataset to link and connect Potential Human-Trafficking Operations on Text Escort Advertisements
• Can Authorship Representation Learning Capture Stylistic Features?
• Towards a Common Understanding of Contributing Factors for Cross-Lingual Transfer in Multilingual Language Models: A Review
• Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression
• Same Author or Just Same Topic? Towards Content-Independent Style Representations
• Match the Script, Adapt if Multilingual: Analyzing the Effect of Multilingual Pretraining on Cross-lingual Transferability
• Idiosyncratic but not Arbitrary: Learning Idiolects in Online Registers Reveals Distinctive yet Consistent Individual Styles
• Can contrastive learning avoid shortcut solutions?
• The Topic Confusion Task: A Novel Scenario for Authorship Attribution
• Unsupervised Cross-lingual Representation Learning at Scale
• RoBERTa: A Robustly Optimized BERT Pretraining Approach
• Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond
• Representation Learning with Contrastive Predictive Coding
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Related

• Authorship Attribution in Multilingual Machine-Generated Texts
• Enhancing Authorship Attribution through Embedding Fusion: A Novel Approach with Masked and Encoder-Decoder Language Models
• Whodunit? Learning to Contrast for Authorship Attribution
• Enhancing Representation Generalization in Authorship Identification
• Towards Effective Authorship Attribution: Integrating Class-Incremental Learning