works on
language resources 1llm bias 1multilingual evaluation 1reward models 1safety filtering 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.CL2026

Lower-Resource, Higher Scores: Language Bias in LLM Evaluators

Ej Zhou, Lucas Resck, Zheng Hui +1

The paper shows that large language model evaluators give systematically different scores to the same content in different languages, favoring lower‑resource languages, even though…