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

arXiv: https://arxiv.org/abs/2604.07119 · HTML: https://mlsanity.com/paper/2604.07119/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 23 references that are in the map.
- First posted on arXiv 8 Apr 2026.

## Builds on (most cited first, 6 of 6)

- [An Open Review of OpenReview: A Critical Analysis of the Machine Learning Conference Review Process](https://mlsanity.com/paper/2010.05137/) (2020)
- [Automatic Analysis of Substantiation in Scientific Peer Reviews](https://mlsanity.com/paper/2311.11967/) (2023)
- [LazyReview A Dataset for Uncovering Lazy Thinking in NLP Peer Reviews](https://mlsanity.com/paper/2504.11042/) (2025)
- [The Nature of NLP: Analyzing Contributions in NLP Papers](https://mlsanity.com/paper/2409.19505/) (2024)
- [Uncovering Latent Biases in Text: Method and Application to Peer Review](https://mlsanity.com/paper/2010.15300/) (2020)
- ["You Cannot Sound Like GPT": Signs of language discrimination and resistance in computer science publishing](https://mlsanity.com/paper/2505.08127/) (2025)

## Abstract (arXiv)

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 an LLM-based detection pipeline achieving 87.37 macro F1. 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.