Mitigating Translationese Bias in Multilingual LLM-as-a-Judge via Disentangled Information Bottleneck

ArXi:2603.10351v1 Announce Type: cross Large language models (LLMs) have become a standard for multilingual evaluation, yet they exhibit a severe systematic translationese bias. In this paper, translationese bias is characterized as LLMs systematically favoring machine-translated text over human-authored references, particularly in low-resource languages. We attribute this bias to spurious correlations with (i) latent manifold alignment with English and (ii) cross-lingual predictability.