Ingest-And-Ground：用RAG消除持续预训练LLM的幻觉
Ingest-And-Ground: Dispelling Hallucinations from Continually-Pretrained LLMs with RAG
AI总结：
本文提出Ingest-And-Ground方法，通过隐私知识库持续预训练基础LLM并增强语义RAG层，有效减少幻觉，在隐私查询处理上性能指标较开箱即用LLM最多翻倍。
摘要：
本文提出有望利用LLM和RAG提升隐私流程效率的新方法。为减少幻觉，我们用隐私专属知识库持续预训练基础LLM模型，随后用语义RAG层对其进行增强。评估表明，该方法通过用事实信息为响应提供依据来减少不准确之处，从而在处理隐私相关查询时提升了模型性能（与开箱即用的LLM相比指标最多翻倍）。
英文摘要：
This paper presents new methods that have the potential to improve privacy process efficiency with LLM and RAG. To reduce hallucination, we continually pre-train the base LLM model with a privacy-specific knowledge base and then augment it with a semantic RAG layer. Our evaluations demonstrate that this approach enhances the model performance (as much as doubled metrics compared to out-of-box LLM) in handling privacy-related queries, by grounding responses with factual information which reduces inaccuracies.
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。
