对比RAG与微调在工业问答中的效果，发现RAG更省成本且效果好。
Assessment of RAG and Fine-Tuning for Industrial Question-Answering-Applications
- 用检索增强生成（RAG）提升开源模型的问答能力
- 在汽车领域数据上，RAG让开源模型表现接近顶级闭源模型
- 适合追求低成本高效率的企业级问答系统部署
大型语言模型在企业问答系统中应用日益广泛，需适配领域知识。当前主流方法为检索增强生成（RAG）与微调（FT），但从成本与准确率权衡角度看，二者在产业场景中的适用性尚不明确。本研究基于两个面向汽车行业的封闭数据集，评估RAG与FT在答案质量与运行成本方面的影响。我们扩展了Erol等人提出的Cost-of-Pass框架，综合评估输出质量、生成成本与用户交互成本。结果表明，尽管高端模型初始性能最优，但通过RAG增强后，开源模型可达到相近水平。总体而言，无论对于闭源还是开源模型，RAG均是更有效且成本更低的适应方法。
原文摘要 · Abstract (English)
Large Language Models (LLMs) are increasingly employed in enterprise question-answering (QA) systems, requiring adaptation to domain-specific knowledge. Among the most prevalent methods for incorporating such knowledge are Retrieval-Augmented Generation (RAG) and fine-tuning (FT). Yet, from a cost-accuracy trade-off perspective, it remains unclear which approach best suits industry scenarios. This study examines the impact of RAG and FT on two closed datasets specific to the automotive industry, assessing answer quality and operational costs. We extend the Cost-of-Pass framework proposed by Erol et al. (arXiv:2504.13359) to jointly assess output quality, generation cost, and user interaction cost. Our findings reveal that while premium models perform best out of the box, open-source models can achieve comparable quality when enhanced with RAG. Overall, RAG emerges as the most effective and cost-efficient adaptation method for both closed- and open-source models.
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。