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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Hongbin, Chen, Kehai, Bai, Xuefen, Pan, Youcheng, Xiang, Yang, Wang, Jinpeng, Zhang, Min
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911504482172928
author Zhang, Hongbin
Chen, Kehai
Bai, Xuefen
Pan, Youcheng
Xiang, Yang
Wang, Jinpeng
Zhang, Min
author_facet Zhang, Hongbin
Chen, Kehai
Bai, Xuefen
Pan, Youcheng
Xiang, Yang
Wang, Jinpeng
Zhang, Min
contents 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. To mitigate this bias, we propose DIBJudge, a robust fine-tuning framework that learns a minimally sufficient, judgment-critical representation via variational information compression, while explicitly isolating spurious factors into the dedicated bias branch. Furthermore, we incorporate a cross-covariance penalty that explicitly suppresses statistical dependence between robust and bias representations, thereby encouraging effective disentanglement. Extensive evaluations on multilingual reward modeling benchmarks and a dedicated translationese bias evaluation suite demonstrate that the proposed DIBJudge consistently outperforms strong baselines and substantially mitigates translationese bias.
format Preprint
id arxiv_https___arxiv_org_abs_2603_10351
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Mitigating Translationese Bias in Multilingual LLM-as-a-Judge via Disentangled Information Bottleneck
Zhang, Hongbin
Chen, Kehai
Bai, Xuefen
Pan, Youcheng
Xiang, Yang
Wang, Jinpeng
Zhang, Min
Computation and Language
Artificial Intelligence
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. To mitigate this bias, we propose DIBJudge, a robust fine-tuning framework that learns a minimally sufficient, judgment-critical representation via variational information compression, while explicitly isolating spurious factors into the dedicated bias branch. Furthermore, we incorporate a cross-covariance penalty that explicitly suppresses statistical dependence between robust and bias representations, thereby encouraging effective disentanglement. Extensive evaluations on multilingual reward modeling benchmarks and a dedicated translationese bias evaluation suite demonstrate that the proposed DIBJudge consistently outperforms strong baselines and substantially mitigates translationese bias.
title Mitigating Translationese Bias in Multilingual LLM-as-a-Judge via Disentangled Information Bottleneck
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2603.10351