按需語言，知識為核：結合編解碼器翻譯模型與LLM構建可擴展多語言系統

Language on Demand, Knowledge at Core: Composing LLMs with Encoder-Decoder Translation Models for Extensible Multilinguality

March 18, 2026

作者: Mengyu Bu, Yang Feng

cs.AI

摘要

大型语言模型（LLMs）展现出强大的通用智能，但其多语言性能仍存在显著不平衡。尽管LLMs在统一语义空间中编码了丰富的跨语言知识，却往往难以可靠地将这些知识接口应用于低资源或未见语言。值得庆幸的是，预训练的编码器-解码器翻译模型已具备均衡的多语言能力，这为LLMs提供了天然的补充。本研究提出XBridge框架——一种组合式编码器-LLM-解码器架构，该架构将多语言理解与生成任务卸载给外部预训练翻译模型，同时保留LLM作为英语核心处理器以承担通用知识处理。针对由此产生的模型间表征失准问题，我们引入轻量级跨模型映射层和基于最优传输的对齐目标，从而实现细粒度语义一致的多语言生成。在涵盖多语言理解、推理、摘要和生成的四个LLM上的实验表明，XBridge在低资源及未见语言场景下显著优于强基线模型，且无需对LLM进行重新训练。

English

Large language models (LLMs) exhibit strong general intelligence, yet their multilingual performance remains highly imbalanced. Although LLMs encode substantial cross-lingual knowledge in a unified semantic space, they often struggle to reliably interface this knowledge with low-resource or unseen languages. Fortunately, pretrained encoder-decoder translation models already possess balanced multilingual capability, suggesting a natural complement to LLMs. In this work, we propose XBridge, a compositional encoder-LLM-decoder architecture that offloads multilingual understanding and generation to external pretrained translation models, while preserving the LLM as an English-centric core for general knowledge processing. To address the resulting representation misalignment across models, we introduce lightweight cross-model mapping layers and an optimal transport-based alignment objective, enabling fine-grained semantic consistency for multilingual generation. Experiments on four LLMs across multilingual understanding, reasoning, summarization, and generation indicate that XBridge outperforms strong baselines, especially on low-resource and previously unseen languages, without retraining the LLM.