AI RESEARCH
Domain-Specific Quality Estimation for Machine Translation in Low-Resource Scenarios
arXiv CS.LG
•
ArXi:2603.07372v1 Announce Type: cross Quality Estimation (QE) is essential for assessing machine translation quality in reference-less settings, particularly for domain-specific and low-resource language scenarios. In this paper, we investigate sentence-level QE for English to Indic machine translation across four domains (Healthcare, Legal, Tourism, and General) and five language pairs. We systematically compare zero-shot, few-shot, and guideline-anchored prompting across selected closed-weight and open-weight LLMs.