2026
How Does Alignment Enhance LLMs’ Multilingual Capabilities? A Language Neurons Perspective
AAAI 2026technical
Multilingual Alignment is an effective and representative paradigm to enhance LLMs
3 accepted papers
Multilingual Alignment is an effective and representative paradigm to enhance LLMs
Quality Estimation (QE) models evaluate the quality of machine translations without reference translations, serving as the reward models for the translation task.Due to the data scarcity, synthetic data generation has emerged as a promising solution.However, synthetic QE data often suffers from dist…
Machine translation (MT) quality estimation (QE) is a crucial task to estimate the quality of MT outputs when reference translations are unavailable. Many studies focus on generating pseudo data using large parallel corpus and achieve remarkable success in the supervised setting. However, pseudo dat…