ACT-MNMT Auto-Constriction Turning for Multilingual Neural Machine Translation

arXiv:2403.06745v1 Announce Type: new
Abstract: Large language model (LLM) has achieved promising performance in multilingual machine translation tasks through zero/few-shot prompts or prompt-tuning. However, due to the mixture of multilingual data during the pre-training of LLM, the LLM-based translation models face the off-target issue in both prompt-based methods, including a series of phenomena, namely instruction misunderstanding, translation with wrong language and over-generation. For this issue, this paper introduces an \textbf{\underline{A}}uto-\textbf{\underline{C}}onstriction \textbf{\underline{T}}urning mechanism for \textbf{\underline{M}}ultilingual \textbf{\underline{N}}eural \textbf{\underline{M}}achine \textbf{\underline{T}}ranslation (\model), which is …

abstract act arxiv auto cs.ai cs.cl data face few-shot however issue language language model large language large language model llm machine machine translation multilingual neural machine translation performance pre-training prompt prompts series tasks through training translation type