AI RESEARCH

Do LLMs Truly Benefit from Longer Context in Automatic Post-Editing?

arXiv CS.CL

ArXi:2601.19410v3 Announce Type: replace Automatic post-editing (APE) aims to refine machine translations by correcting residual errors. Although recent large language models (LLMs) nstrate strong translation capabilities, their effectiveness for APE--especially under document-level context--remains insufficiently understood. We present a systematic comparison of Our results show that