AI RESEARCH
What Does LLM Refinement Actually Improve? A Systematic Study on Document-Level Literary Translation
arXiv CS.CL
•
ArXi:2605.13368v1 Announce Type: new Iterative self-refinement is a simple inference-time strategy for machine translation: an LLM revises its own translation over multiple inference-time passes. Yet document-scale refinement remains poorly understood: 1) which pipelines work best, 2) what quality dimensions improve, and 3) how refiners behave. In this paper, we present a systematic study of document-level literary translation, covering nine LLMs and seven language pairs.