Multilingual RAG rerankers exhibit language bias that limits cross-lingual evidence use, and the proposed LAURA method aligns ranking with downstream generation utility to reduce the bias and improve performance.
Faux Polyglot: A Study on Information Disparity in Multilingual Large Language Models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAG
Multilingual RAG rerankers exhibit language bias that limits cross-lingual evidence use, and the proposed LAURA method aligns ranking with downstream generation utility to reduce the bias and improve performance.