用代码统一多语言信息抽取，让大模型跨语言能力更强
KnowCoder-X: Boosting Multilingual Information Extraction via Code
- 用Python类统一多语言信息抽取模板，将任务转为代码生成
- 在25.7万条双语数据上训练，跨语言性能超ChatGPT 30.17%
- 无需训练就能处理29种未见语言，适合多语言信息提取场景
实证表明大语言模型具备自发的跨语言对齐能力，但在信息抽取（IE）任务中，语言间仍存在显著不平衡。为此，我们提出KnowCoder-X，一种具备先进跨语言与多语言能力的代码型大模型，适用于通用信息抽取。首先，采用Python类标准化多语言模式表示，确保不同语言间本体一致；其次，将跨语言信息抽取转化为统一的代码生成任务。我们还在翻译后的实例预测任务上进行跨语言对齐指令微调，并构建了包含25.7万样本的高质量双语信息抽取平行数据集ParallelNER，通过三阶段稳健流水线生成并人工校验质量。尽管未在29种未见语言上训练，KnowCoder-X在跨语言性能上仍比ChatGPT高30.17%，比现有最佳方法（SoTA）高20.03%。在中英文64个基准上的全面评估表明，KnowCoder-X显著提升了跨语言信息抽取的迁移能力。代码与数据集已开源。
原文摘要 · Abstract (English)
Empirical evidence indicates that LLMs exhibit spontaneous cross-lingual alignment. However, although LLMs show promising cross-lingual alignment in Information Extraction (IE), a significant imbalance across languages persists, highlighting an underlying deficiency. To address this, we propose KnowCoder-X, a powerful code LLM with advanced cross-lingual and multilingual capabilities for universal IE. Firstly, it standardizes the representation of multilingual schemas using Python classes, ensuring a consistent ontology across different languages. Then, IE across languages is formulated as a unified code generation task. Secondly, we conduct IE cross-lingual alignment instruction tuning on the translated instance prediction task to enhance the model's cross-lingual transferability. During this phase, we also construct a high-quality and diverse bilingual IE parallel dataset with 257k samples, called ParallelNER, synthesized by our proposed robust three-stage pipeline, with manual annotation to ensure quality. Although without training in 29 unseen languages, KnowCoder-X surpasses ChatGPT by 30.17\% and SoTA by 20.03\%, thereby demonstrating superior cross-lingual IE capabilities. Comprehensive evaluations on 64 IE benchmarks in Chinese and English under various settings demonstrate that KnowCoder-X significantly enhances cross-lingual IE transfer through boosting the IE alignment. Our code and dataset are available at: https://github.com/ICT-GoKnow/KnowCoder
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。