用轻量适配器融合实现多语言文本转Cypher的增量扩展
Incremental Multilingual Text2Cypher with Adapter Combination
- 为多语言分别训练LoRA适配器，通过学习型融合网络动态组合
- 融合MLP达到联合微调75%的准确率，仅需少量数据
- 新增语言只需一个适配器+轻量重训，适合实际部署场景
大型语言模型使用户可通过自然语言接口访问数据库，如Text2SQL、Text2SPARQL和Text2Cypher，将用户问题转化为结构化查询。尽管这些系统提升了数据库可访问性，但多数研究集中于英语，多语言支持有限。本文提出一种可扩展的多语言Text2Cypher方法，旨在支持新语言时无需重新进行全量微调，避免手动调参，并保持性能接近联合多语言微调。我们为英语、西班牙语和土耳其语分别训练了语言特定的LoRA适配器，并通过统一线性合并或学习型融合MLP与动态门控进行组合。实验结果表明，融合MLP在仅使用更小数据子集的情况下，恢复了约75%的联合多语言微调准确率增益，且在三种语言上均优于线性合并。该方法可通过仅训练一个LoRA适配器和轻量级MLP实现新语言的增量扩展。学习型适配器融合为昂贵的联合微调提供了实用替代方案，在性能、数据效率与可扩展性之间取得平衡。
原文摘要 · Abstract (English)
Large Language Models enable users to access database using natural language interfaces using tools like Text2SQL, Text2SPARQL, and Text2Cypher, which translate user questions into structured database queries. While these systems improve database accessibility, most research focuses on English with limited multilingual support. This work investigates a scalable multilingual Text2Cypher, aiming to support new languages without re-running full fine-tuning, avoiding manual hyper-parameter tuning, and maintaining performance close to joint multilingual fine-tuning. We train language-specific LoRA adapters for English, Spanish, and Turkish and combined them via uniform linear merging or learned fusion MLP with dynamic gating. Experimental results show that the fusion MLP recovers around 75\% of the accuracy gains from joint multilingual fine-tuning while requiring only a smaller subset of the data, outperforming linear merging across all three languages. This approach enables incremental language expansion to new languages by requiring only one LoRA adapter and a lightweight MLP retraining. Learned adapter fusion offers a practical alternative to expensive joint fine-tuning, balancing performance, data efficiency, and scalability for multilingual Text2Cypher task.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。