# MultiGhostBench: A Multilingual Benchmark for Long-Form LLM-Generated Text Attribution under Distribution Shifts

arXiv: https://arxiv.org/abs/2609.02379 · HTML: https://mlsanity.com/paper/2609.02379/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 51 references that are in the map.
- First posted on arXiv 2 Sep 2026.

## Builds on (most cited first, 30 of 31)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [GLTR: Statistical Detection and Visualization of Generated Text](https://mlsanity.com/paper/1906.04043/) (2019)
- [Texygen: A Benchmarking Platform for Text Generation Models](https://mlsanity.com/paper/1802.01886/) (2018)
- [MEGA: Multilingual Evaluation of Generative AI](https://mlsanity.com/paper/2303.12528/) (2023)
- [RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectors](https://mlsanity.com/paper/2405.07940/) (2024)
- [German's Next Language Model](https://mlsanity.com/paper/2010.10906/) (2020)
- [DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text](https://mlsanity.com/paper/2305.17359/) (2023)
- [TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation](https://mlsanity.com/paper/2109.13296/) (2021)
- [Adaptation of Deep Bidirectional Multilingual Transformers for Russian Language](https://mlsanity.com/paper/1905.07213/) (2019)
- [Human heuristics for AI-generated language are flawed](https://mlsanity.com/paper/2206.07271/) (2022)
- [Spanish Pre-trained BERT Model and Evaluation Data](https://mlsanity.com/paper/2308.02976/) (2023)
- [Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation](https://mlsanity.com/paper/2208.11646/) (2022)
- [Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages](https://mlsanity.com/paper/2410.16153/) (2024)
- [DeTeCtive: Detecting AI-generated Text via Multi-Level Contrastive Learning](https://mlsanity.com/paper/2410.20964/) (2024)
- [Standardizing the Measurement of Text Diversity: A Tool and a Comparative Analysis of Scores](https://mlsanity.com/paper/2403.00553/) (2024)
- [A Primer on Pretrained Multilingual Language Models](https://mlsanity.com/paper/2107.00676/) (2021)
- [Authorship Attribution in the Era of LLMs: Problems, Methodologies, and Challenges](https://mlsanity.com/paper/2408.08946/) (2024)
- [EditLens: Quantifying the Extent of AI Editing in Text](https://mlsanity.com/paper/2510.03154/) (2025)
- [Summarize, Outline, and Elaborate: Long-Text Generation via Hierarchical Supervision from Extractive Summaries](https://mlsanity.com/paper/2010.07074/) (2020)
- [Navigating the Path of Writing: Outline-guided Text Generation with Large Language Models](https://mlsanity.com/paper/2404.13919/) (2024)
- [Self-Repetition in Abstractive Neural Summarizers](https://mlsanity.com/paper/2210.08145/) (2022)
- [AI use in American newspapers is widespread, uneven, and rarely disclosed](https://mlsanity.com/paper/2510.18774/) (2025)
- [OpenTuringBench: An Open-Model-based Benchmark and Framework for Machine-Generated Text Detection and Attribution](https://mlsanity.com/paper/2504.11369/) (2025)
- [Authorship Attribution in Multilingual Machine-Generated Texts](https://mlsanity.com/paper/2508.01656/) (2025)
- [Towards Reliable Detection of LLM-Generated Texts: A Comprehensive Evaluation Framework with CUDRT](https://mlsanity.com/paper/2406.09056/) (2024)
- [CEAID: Benchmark of Multilingual Machine-Generated Text Detection Methods for Central European Languages](https://mlsanity.com/paper/2509.26051/) (2025)

## Abstract (arXiv)

While existing work on LLM authorship attribution (AA) has made progress, available benchmarks remain limited, often focusing on English, controlled settings, or relatively outdated models, with the few multilingual studies considering only relatively short texts. We introduce MultiGhostBench, a multilingual benchmark comprising 928 books generated by five recent LLMs across six languages and three scripts, with an average length of approximately 59K words per book. The benchmark supports evaluation under domain, author, and language shifts. Evaluation of representative AA methods shows that no single method consistently performs best across settings, and performance generally degrades under distribution shifts. Transformer-based detectors can retain generator-related information across languages, although transfer effectiveness varies by language pair, whereas statistical and fingerprint-based detectors are more language-dependent. We envision MultiGhostBench as a valuable resource for the development and evaluation of robust AA methods. The dataset and code can be found at https://github.com/GrecoMT/MultiGhostBench.