Can an Old Dog Be Taught New Tricks? Taking LLMs Beyond Sentence Level Translation
arXiv cs.CL2w4 min read
arXiv:2607.14040v1 Announce Type: new Abstract: Automatic translation systems, from CAT tools to MT, overwhelmingly treat translation as a sentence-by-sentence act. This paper asks whether LLMs can be moved beyond that paradigm through whole-document, corpus-informed translation. We present PAT (Pragmatic Auto-Translator), a RAG-based system that pairs user-configured specifications with context from a comparable corpus of authentic longform texts in U.S. English and Latin American Spanish, passing retrieved paragraph-, section-, and document-level examples to an LLM for whole-document generat