As MT quality increases, interest in enhanced post-editing features such as QE-derived error highlights is growing, yet evidence for their usefulness remains limited. In this work, we explore the usefulness of LLM-derived error highlights and correction suggestions based on automatic post-editing (APE). We conduct a study where professional translators (En-Nl) post-edit translations using APE error highlights and correction suggestions and compare productivity, quality and user experience to regular PE and PE with QE-derived highlights. While no condition yielded productivity or quality gains compared to regular PE, APE highlights were better received than QE-derived highlights, and correction suggestions improved overall user experience.
Cite
@article{arxiv.2605.21135,
title = {Smarter edits? Post-editing with error highlights and translation suggestions},
author = {Fleur V. J. van Tellingen and Gautam Ranka and Dora Žugčić and Joyce van der Wal and Andrea Camasta and Livio Guerra and Alina Karakanta},
journal= {arXiv preprint arXiv:2605.21135},
year = {2026}
}