Hugging Face Trending Papers August 20, 2026

Auditing Cross-Lingual Fairness in Language Model Watermarking

Read the original on Hugging Face Trending Papers →

Watermarking schemes for large language model output are evaluated almost exclusively on English text using each scheme's detection threshold and a narrow set of quality measurements. Multilingual deployment exposes evaluation-design choices that are inconsequential on English but determine conclusions cross-lingually.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

arXiv Machine Learning

Aug 21

Auditing Cross-Lingual Fairness in Language Model Watermarking

arXiv:2608. 20047v1 Announce Type: cross Abstract: Watermarking schemes for large language model output are evaluated almost exclusively on English text using each scheme's detection threshold and a narrow set of quality measurements.

By Alexander Nemecek, Osama Zafar, Debargha Ganguly, Vikash Singh, Vipin Chaudhary, Erman Ayday

llms safety

arXiv AI

Jun 2

Linguistics-Aware Non-Distortionary LLM Watermarking

arXiv:2606. 00613v1 Announce Type: cross Abstract: Watermarking should identify language-model output without degrading quality or limiting verification to the model provider.

By Shinwoo Park, Hyejin Park, Hyeseon An, Yo-Sub Han

llms computer-vision nlp

arXiv Machine Learning

Aug 17

Semantic Differentiation for Tackling Challenges in Watermarking Low-Entropy Constrained Generation Outputs

arXiv:2601. 11629v2 Announce Type: replace-cross Abstract: We demonstrate that while the current approaches for language model watermarking are effective for open-ended generation, they are inadequate at watermarking LM outputs for constrained generation tasks with low-entropy output spaces.

By Nghia T. Le, Alan Ritter, Kartik Goyal

llms nlp

arXiv Machine Learning

Jun 18

Signature filtering: a lightweight enhancement for statistical watermark detection in large language models

arXiv:2606. 18430v1 Announce Type: new Abstract: Statistical watermarks help organizations attribute large language model (LLM) outputs, yet existing detectors often struggle when watermark signals are weak, texts are repetitive, or watermarks are edited.

By Chih-Duo Hong, Yen-Pang Chen, Fang Yu

llms rag benchmarks

arXiv Machine Learning

Jul 8

Beyond Heuristic Tuning: Power-Calibrated LLM Watermarking

arXiv:2607. 05694v1 Announce Type: cross Abstract: Logit-based watermarking is a widely used mechanism for identifying LLM generated content, yet its effectiveness is governed by a fundamental trade-off between detectability and semantic distortion.

By Xiaopu Wang, Zelin He, Chengyuan Liu, Runze Li

llms

arXiv Computation and Language

3d ago

Apples to Apples? Towards Comparable Crosslingual Language Model Evaluation

The paper investigates how to fairly compare language models across languages, noting that current evaluation methods vary widely and lack empirical validation. By training controlled monolingual models on parallel data and testing multilingual LLMs, the authors find that many normalized metrics suffer from biases due to tokenization, encoding, and orthographic differences. Instead, they recommend using sentence‑level negative log‑likelihood over semantically equivalent sequences for more reliable cross‑lingual comparisons.

By Xiulin Yang, Ethan Gotlieb Wilcox, Catherine Arnett

llms nlp

One email a morning, machine-written

Related stories

Auditing Cross-Lingual Fairness in Language Model Watermarking

Linguistics-Aware Non-Distortionary LLM Watermarking

Semantic Differentiation for Tackling Challenges in Watermarking Low-Entropy Constrained Generation Outputs

Signature filtering: a lightweight enhancement for statistical watermark detection in large language models

Beyond Heuristic Tuning: Power-Calibrated LLM Watermarking

Apples to Apples? Towards Comparable Crosslingual Language Model Evaluation