Languageagnostic Utilitydriven Reranker Alignment Laura
1 mentions across 0 people
All mentions
Unknown speaker
Recommendedpaper · 2026-04-23
“To bridge this gap, we propose Language-Agnostic Utility-driven Reranker Alignment (LAURA), which aligns multilingual evidence ranking with downstream generative utility.”
mRAG Rerankers Exhibit Severe Language Bias Favoring English, Mitigated by Utili ↗