一作ACL 2026Findings· Findings of ACL
Ready to Translate, Not to Represent? Bias and Performance Gaps in Multilingual LLM s Across Language Families and Domains
Md. Faiyaz Abdullah Sayeedi · Subhey Sadi Rahman · Md. Mahbub Alam · Md. Adnanul Islam · Jannatul Ferdous Deepti · Tasnim Mohiuddin · Md Mofijul Islam · Swakkhar Shatabda
摘要
The rise of Large Language Models (LLMs) has redefined Machine Translation (MT), enabling context-aware and fluent translations across hundreds of languages and textual domains. Despite their remarkable capabilities, LLMs often exhibit uneven performance across language families and specialized d...