Beyond post-editing: A project-based module on MT and LLM integration for trainee translators

Alina Karakanta presented a project-based translation technology module for MA Translation students that integrates large language models as translation engines, prompting and domain adaptation tools, and explainable quality estimation signals, according to a paper published in the Proceedings of the 1st International Workshop on Teaching AI-Based Translation and Technologies (TAITT 2026), pages 52–62. Data collected across three years of the module show a gradual shift in students' engine selection and customisation preferences toward LLM-based tools, while traditional engines and built-in options remain a firm presence in their practices. The syllabus covers end-to-end technology assessment, from engine selection and domain adaptation to automatic and human evaluation, post-editing, and reporting results, applied in a simulated client scenario.

Abstract With the rapid technologisation of translation, skills beyond post-editing PE , such as data literacy, technology evaluation, and critical engagement with AI-based tools are becoming essential competencies for trainee translators. This paper presents a syllabus for a translation technology module that equips MA Translation students with end-to-end technology assessment skills, from engine selection and domain adaptation to automatic and human evaluation, post-editing, and reporting results. Large language models are integrated throughout, as translation engines, as a basis for prompting and domain adaptation strategies, and as a source of explainable quality estimation signals. Students apply these skills in a simulated client scenario as project-based learning. Trends on students’ engine selection and customisation preferences observed across three years suggest a gradual shift towards LLM-based tools, but traditional engines and built-in options remain a firm presence in their practices. - Anthology ID: - 2026.taitt-1.7 - Volume: - Proceedings of the 1st International Workshop on Teaching AI-Based Translation and Technologies TAITT 2026 https://aclanthology.org/volumes/2026.taitt-1/ - Month: - June - Year: - 2026 - Address: - Tilburg, the Netherlands - Editors: - Ralph Krüger https://aclanthology.org/people/ralph-kruger/unverified/ , Dorothy Kenny https://aclanthology.org/people/dorothy-kenny/unverified/ , Sheila Castilho https://aclanthology.org/people/sheila-castilho/unverified/ , Sergi Álvarez-Vidal https://aclanthology.org/people/sergi-alvarez-vidal/ , Nora Aranberri https://aclanthology.org/people/nora-aranberri/unverified/ , María Isabel Rivas Ginel https://aclanthology.org/people/maria-isabel-rivas-ginel/unverified/ , Janiça Hackenbuchner https://aclanthology.org/people/janica-hackenbuchner/ - Venues: - TAITT https://aclanthology.org/venues/taitt/ | WS https://aclanthology.org/venues/ws/ - SIG: - Publisher: - European Association for Machine Translation - Note: - Pages: - 52–62 - Language: - URL: - https://aclanthology.org/2026.taitt-1.7/ https://aclanthology.org/2026.taitt-1.7/ - DOI: - Cite ACL : - Alina Karakanta. 2026. Beyond post-editing: A project-based module on MT and LLM integration for trainee translators https://aclanthology.org/2026.taitt-1.7/ . In Proceedings of the 1st International Workshop on Teaching AI-Based Translation and Technologies TAITT 2026 , pages 52–62, Tilburg, the Netherlands. European Association for Machine Translation. - Cite Informal : - Beyond post-editing: A project-based module on MT and LLM integration for trainee translators https://aclanthology.org/2026.taitt-1.7/ Karakanta, TAITT 2026 - PDF: - https://aclanthology.org/2026.taitt-1.7.pdf https://aclanthology.org/2026.taitt-1.7.pdf