# Fusing Stylometric and Embedding Systems to Estimate Authorship Likelihood Ratios in Japanese

arXiv: https://arxiv.org/abs/2606.13991 · HTML: https://mlsanity.com/paper/2606.13991/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 125 references that are in the map.
- First posted on arXiv 12 Jun 2026.

## Builds on (most cited first, 14 of 14)

- [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)
- [Text Classification via Large Language Models](https://mlsanity.com/paper/2305.08377/) (2023)
- [Generative AI Text Classification using Ensemble LLM Approaches](https://mlsanity.com/paper/2309.07755/) (2023)
- [On the State of the Art in Authorship Attribution and Authorship Verification](https://mlsanity.com/paper/2209.06869/) (2022)
- [Are You Robert or RoBERTa? Deceiving Online Authorship Attribution Models Using Neural Text Generators](https://mlsanity.com/paper/2203.09813/) (2022)
- [DeepStyle: User Style Embedding for Authorship Attribution of Short Texts](https://mlsanity.com/paper/2103.11798/) (2021)
- [Deep Bayes Factor Scoring for Authorship Verification](https://mlsanity.com/paper/2008.10105/) (2020)
- [Stylometry Analysis of Multi-authored Documents for Authorship and Author Style Change Detection](https://mlsanity.com/paper/2401.06752/) (2024)
- [Grammar as a Behavioral Biometric: Using Cognitively Motivated Grammar Models for Authorship Verification](https://mlsanity.com/paper/2403.08462/) (2024)
- [Statistical Models in Forensic Voice Comparison](https://mlsanity.com/paper/1912.13242/) (2019)
- [Self-Calibrating Neural-Probabilistic Model for Authorship Verification Under Covariate Shift](https://mlsanity.com/paper/2106.11196/) (2021)
- [Forensic strength of evidence statements should preferably be likelihood ratios calculated using relevant data, quantitative measurements, and statistical models](https://mlsanity.com/paper/2012.12198/) (2020)
- [Integrated ensemble of BERT- and features-based models for authorship attribution in Japanese literary works](https://mlsanity.com/paper/2504.08527/) (2025)

## Abstract (arXiv)

The likelihood ratio framework is widely recognized as the logically and legally sound basis for evidential analysis across forensic sciences, and its importance is increasingly acknowledged in analyses of authorship in textual evidence. To date, however, its application has been confined to English-language texts. Meanwhile, authorship attribution has traditionally relied on a diverse array of stylometric features, even as the rise of pre-trained large language models enables new contextual-embedding approaches. Combining these diverse approaches through fusion promises enhanced performance, yet it has not been applied to integrate stylometric-feature systems with embedding-based systems within the likelihood ratio paradigm. This study is the first to apply likelihood ratio-based forensic text comparison to Japanese digital texts, using ~1,000-character excerpts from blogs, to 1) evaluate system performance and likelihood ratio magnitudes and 2) assess the impact of fusing stylometric-feature systems with embedding-based systems. The results demonstrate that the fused system maintains excellent calibration while 1) increasing consistent-with-fact likelihood ratio magnitudes; 2) decreasing contrary-to-fact likelihood ratio magnitudes and 3) improving overall discriminability. The best-performing fusion achieved a log-likelihood-ratio cost of 0.32484, illustrating both the feasibility of likelihood ratio framework for Japanese and the benefits of fusion across heterogeneous systems.