针对土耳其语的RAG最佳实践，实测高效低成本方案。
RAGTurk: Best Practices for Retrieval Augmented Generation in Turkish
- 构建土耳其语专用RAG数据集，覆盖问答与段落
- 复杂方法准确率达85%，低于基线7.3个百分点
- 简单查询澄清+强重排序可低耗达84.6%性能
检索增强生成（RAG）提升大模型事实准确性，但现有设计指导以英语为主，难以适用于构词丰富的语言如土耳其语。本文基于土耳其维基百科和CulturaX构建了全面的土耳其语RAG数据集，包含问答对与相关段落片段。我们对RAG流程七个阶段（从查询转换、重排序到答案精炼）进行了基准测试，未使用任务特定微调。结果表明，复杂方法如HyDE可将准确率提升至85%，显著高于基线78.70%。同时，采用交叉编码器重排序与上下文增强的帕累托最优配置，在大幅降低计算成本的同时，达到84.60%的性能表现。进一步发现，过度堆叠生成模块会扭曲形态线索，导致性能下降；而通过稳健重排序实现简单查询澄清，反而更有效。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) enhances LLM factuality, yet design guidance remains English-centric, limiting insights for morphologically rich languages like Turkish. We address this by constructing a comprehensive Turkish RAG dataset derived from Turkish Wikipedia and CulturaX, comprising question-answer pairs and relevant passage chunks. We benchmark seven stages of the RAG pipeline, from query transformation and reranking to answer refinement, without task-specific fine-tuning. Our results show that complex methods like HyDE maximize accuracy (85%) that is considerably higher than the baseline (78.70%). Also a Pareto-optimal configuration using Cross-encoder Reranking and Context Augmentation achieves comparable performance (84.60%) with much lower cost. We further demonstrate that over-stacking generative modules can degrade performance by distorting morphological cues, whereas simple query clarification with robust reranking offers an effective solution.
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。