Are Non-English Papers Reviewed Fairly? Language-of-Study Bias in NLP Peer Reviews

2026-04-08

AI Summary

This study addresses linguistic bias in peer review within natural language processing, where non-English research is often undervalued based on its language rather than scientific merit. The work formally defines and systematically analyzes “language-of-study bias,” identifying four subtypes of negative bias, with “unjustified demands for cross-lingual generalization” being the most prevalent. The authors introduce LOBSTER, a manually annotated dataset, and develop a high-precision detection model achieving a macro F1-score of 87.37. Analysis of 15,645 peer reviews reveals that papers reporting non-English studies face significantly more negative bias—far outweighing any positive bias—highlighting systemic inequities in the review process.

Abstract

Peer review plays a central role in the NLP publication process, but is susceptible to various biases. Here, we study language-of-study (LoS) bias: the tendency for reviewers to evaluate a paper differently based on the language(s) it studies, rather than its scientific merit. Despite being explicitly flagged in reviewing guidelines, such biases are poorly understood. Prior work treats such comments as part of broader categories of weak or unconstructive reviews without defining them as a distinct form of bias. We present the first systematic characterization of LoS bias, distinguishing negative and positive forms, and introduce the human-annotated dataset LOBSTER (Language-Of-study Bias in ScienTific pEer Review) and a method achieving 87.37 macro F1 for detection. We analyze 15,645 reviews to estimate how negative and positive biases differ with respect to the LoS, and find that non-English papers face substantially higher bias rates than English-only ones, with negative bias consistently outweighing positive bias. Finally, we identify four subcategories of negative bias, and find that demanding unjustified cross-lingual generalization is the most dominant form. We publicly release all resources to support work on fairer reviewing practices in NLP and beyond.

Problem

• language-of-study bias
• peer review
• NLP
• non-English papers
• review bias

Innovation

• language-of-study bias
• peer review bias
• LOBSTER dataset
• cross-lingual generalization
• fairness in NLP