HW-TSC-Agent is proposed, a multi-stage translation agent framework that integrates translation model fine-tuning, dual-model candidate generation, and instruction-aware translation refinement into a unified pipeline.
Yu He, Xiao-Qing Lan, Dai-Meng Wei et al.· Proceedings of the Eleventh...· 0 citations
Internet texts are replete with format tags that carry structural, semantic, and functional meaning. Current large language model (LLM)-based translation systems struggle to balance translation fluency with tag fidelity when processing tagged text. We argue that resolving this tension requires a systematic approach at...
Zhanglin Wu, Hengchao Shang, Dai-Meng Wei et al.· 0 citations
Cross-Preference Learning (CPL) is proposed, a preference-based training framework that explicitly captures the complementary benefits of sentence-level and context-aware MT, by integrating both intra- and cross-condition preferences into the preference optimization objective.
Ying Li, Xinglin Lyu, Junhui Li et al.· arXiv.org· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.