Code-Based English Models Surprising Performance on Chinese QA Pair Extraction Task

arXiv:2401.10286v3 Announce Type: replace
Abstract: In previous studies, code-based models have consistently outperformed text-based models in reasoning-intensive scenarios. When generating our knowledge base for Retrieval-Augmented Generation (RAG), we observed that code-based models also perform exceptionally well in Chinese QA Pair Extraction task. Further, our experiments and the metrics we designed discovered that code-based models containing a certain amount of Chinese data achieve even better performance. Additionally, the capabilities of code-based English models in specified Chinese tasks offer a distinct perspective …

abstract arxiv chinese code cs.ai cs.cl english extraction knowledge knowledge base metrics performance rag reasoning retrieval retrieval-augmented studies text type