Smarter edits? Post-editing with error highlights and translation suggestions
A new study explored the effectiveness of LLM-derived error highlights and correction suggestions for professional translators. While the features did not lead to productivity or quality gains compared to standard post-editing, the LLM-based error highlights were better received than those derived from Quality Estimation (QE). The correction suggestions specifically improved the overall user experience for translators working on English-to-Dutch translations. AI