paper-with-me

홈 › Papers

Is Multilingual LLM Watermarking Truly Multilingual? Scaling Robustness to 100+ Languages via Back-Translation

2025-10-20 · Asim Mohamed, Martin Gubri arxiv

Multilingual watermarking aims to make large language model (LLM) outputs traceable across languages, yet current methods still fall short. Despite claims of cross-lingual robustness, they are evaluated only on high-resource languages. We show that existing multilingual watermarking methods are not truly multilingual: they fail to remain robust under translation attacks in medium- and low-resource languages. We trace this failure to semantic clustering, which fails when the tokenizer vocabulary contains too few full-word tokens for a given language. To address this, we introduce STEAM, a detection method that uses Bayesian optimisation to search among 133 candidate languages for the back-translation that best recovers the watermark strength. It is compatible with any watermarking method, robust across different tokenizers and languages, non-invasive, and easily extendable to new languages. With average gains of +0.23 AUC and +37% TPR@1%, STEAM provides a scalable approach toward fairer watermarking across the diversity of languages.

📄 PDF Abstract BibTeX arXiv:2510.18019

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Robust Optimization for Multilingual Translation with Imbalanced Data

2021-04-15 · NeurIPS 2021 12 · Xian Li, Hongyu Gong

Multilingual models are parameter-efficient and especially effective in improving low-resource languages by leveraging crosslingual transfer. Despite recent advance in massive multilingual translation with ever-growing m…

Machine TranslationTranslation

Asymmetric Conflict and Synergy in Post-training for LLM-based Multilingual Machine Translation

2025-02-16 · Tong Zheng, Yan Wen, Huiwen Bao, Junfeng Guo 외

The emergence of Large Language Models (LLMs) has advanced the multilingual machine translation (MMT), yet the Curse of Multilinguality (CoM) remains a major challenge. Existing work in LLM-based MMT typically mitigates …

Machine Translation

BanglaLorica: Design and Evaluation of a Robust Watermarking Algorithm for Large Language Models in Bangla Text Generation

2026-01-08 · Amit Bin Tariqul, A N M Zahid Hossain Milkan, Sahab-Al-Chowdhury, Syed Rifat Raiyan 외 arxiv

As large language models (LLMs) are increasingly deployed for text generation, watermarking has become essential for authorship attribution, intellectual property protection, and misuse detection. While existing watermar…

Text Generation

Not Truly Multilingual: Script Consistency as a Missing Dimension in VLM Evaluation

2026-06-15 · Prabhjot Singh, Bhushan Pawar, Madhu Reddiboina, Rajvee Sheth arxiv

Current multilingual evaluations for Vision-Language Models (VLMs) assume a one-to-one mapping between language and orthography, overlooking billions of users of multi-script languages. We introduce PuMVR (Punjabi Multim…

Visual Reasoning

ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality

2025-10-24 · Shayne Longpre, Sneha Kudugunta, Niklas Muennighoff, I-Hung Hsu 외 arxiv

Scaling laws research has focused overwhelmingly on English -- yet the most prominent AI models explicitly serve billions of international users. In this work, we undertake the largest multilingual scaling laws study to …

Cross-Lingual Transfer