Year: 2026
Type: conference-paper
Abstract: Large Language Models have shown strong performance in Machine Translation, yet they often suffer from paraphrasing errors, omissions, or hallucinations when the input contains translation-specific elements (e.g., URLs, slang, and idioms) that require strict preservation or controlled transformation, undermining the reliability of critical details.We propose CEMT 1 , a Controllable Element-Oriented Machine Translation framework inspired by the analysis-strategy-generation paradigm in human translation.CEMT first employs an Element Detection Module to identify translationspecific elements, and then introduces a Translation Module that decomposes the translation process into linguistically grounded analysis, strategy formulation, and final generation, thereby guiding the reliable translation of these elements.We further introduce a CoT Judge model during training that provides step-wise supervision over the accuracy and consistency of the translation process.On the WMT23/24 Chinese↔English benchmarks, CEMT improves performance over existing Machine Translation models while significantly reducing element-level constraint violations.
Institutions: China Telecom, Xiamen University, China Telecom (China)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166831426