Finetune-RAG: 通过微调语言模型抵抗检索增强生成中的幻觉
Finetune-RAG: Fine-Tuning Language Models to Resist Hallucination in Retrieval-Augmented Generation
AI总结：
Finetune-RAG通过微调方法提升LLM事实准确性，提出首个RAG训练数据集和压力测试评估流程。
摘要：
检索增强生成（RAG）已成为一种强大的框架，通过将输出基于检索到的文档来提高大语言模型（LLMs）的事实性。然而，确保检索到相关信息仍具挑战性，当不相关的内容传递到LLM时，可能导致幻觉。在本工作中，我们提出了Finetune-RAG，一种简单而有效的微调方法，其特点是首个此类RAG训练数据集，旨在模拟现实世界中的不完美性。实验结果表明，Finetune-RAG在基础模型上将事实准确性提高了21.2%。我们还提出了Bench-RAG，一种LLM-as-a-judge评估流程，用于在现实中的不完美检索场景下对模型进行压力测试。我们的代码库和数据集已完全开源供社区使用。
英文摘要：
Retrieval-Augmented Generation (RAG) has emerged as a powerful framework to improve factuality in large language models (LLMs) by grounding their outputs in retrieved documents. However, ensuring perfect retrieval of relevant information remains challenging, and when irrelevant content is passed downstream to an LLM, it can lead to hallucinations. In this work, we propose Finetune-RAG, a simple and effective fine-tuning approach that features the first-of-its-kind RAG training dataset constructed to mimic real-world imperfections. Experimental results show that Finetune-RAG improves factual accuracy by 21.2% over the base model. We also propose Bench-RAG, an LLM-as-a-judge evaluation pipeline that stress tests models under realistic imperfect retrieval scenarios. Our codebase and dataset are fully open sourced for community use.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
