AI ethics evidence index Search
Source-linked daily record
Evidence record 7402 · automatically gathered

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

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

Record details

Published: 11 March 2026
Source: arXiv
Category: Research
Topics: Bias & fairness · Safety & alignment
Retrieved: 14 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Normative Common Ground Replication (NormCoRe): Replication-by-Translation for Studying Norms in Multi-Agent AI

arXiv · 12 March 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

LLM Constitutional Multi-Agent Governance

arXiv · 13 March 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook

arXiv · 16 March 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

The Geometric Inductive Bias of Grokking: Bypassing Phase Transitions via Architectural Topology

arXiv · 5 March 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Age Predictors Through the Lens of Generalization, Bias Mitigation, and Interpretability: Reflections on Causal Implications

arXiv · 17 March 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Prompt Programming for Cultural Bias and Alignment of Large Language Models

arXiv · 17 March 2026

How to cite this record

ethics.ai (11 March 2026), “Mitigating Translationese Bias in Multilingual LLM-as-a-Judge via Disentangled Information Bottleneck,” evidence record 7402, https://ethics.ai/record/7402 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.