2025年5月23日:大型语言模型与检索增强生成(RAG)最新研究进展导读 引言 近年来,大型语言模型(Large Language Models, LLMs)在自然语言处理领域取得了显著进展,并在诸多任务中展现出强大的能力。然而,LLMs仍然面临着知识更新的滞后性以及生成内容可能存在“幻觉”等问题。为了克服这些挑战,检索增强生成(Retrieval-Augmented Generation, RAG)技术应运而生。RAG通过整合外部知识资源,显著提升了LLMs在知识密集型任务中的表现。 本文旨在对截至2025年5月23日新发表的关于LLMs和RAG方向的论文进行梳理和解读,为读者提供最新的研究动态和趋势分析。
近年来,大型语言模型(Large Language Models, LLMs)在自然语言处理领域取得了显著进展,并在诸多任务中展现出强大的能力。然而,LLMs仍然面临着知识更新的滞后性以及生成内容可能存在“幻觉”等问题。为了克服这些挑战,检索增强生成(Retrieval-Augmented Generation, RAG)技术应运而生。RAG通过整合外部知识资源,显著提升了LLMs在知识密集型任务中的表现。
本文旨在对截至2025年5月23日新发表的关于LLMs和RAG方向的论文进行梳理和解读,为读者提供最新的研究动态和趋势分析。
上述论文代表了近期LLMs和RAG领域的一些重要进展,涵盖了RAG的安全性、在医疗和城市研究等领域的应用,以及RAG系统的评估方法等多个方面。这些研究成果为我们更好地理解和应用RAG技术提供了有价值的参考。
未来的研究方向可能包括:
请注意: 本文仅对部分论文进行了简要的总结和分析,更详细的内容请参考原始论文。
Can Large Language Models LLMs and Retrieval Augmented Generation RAG Generate New Knowledge for Urban Studies Sciety Can Large Language Models (LLMs) and Retrieval-Augmented ↩
Investigating Knowledge Graphs as Structured External Memory to Enhance Large Language Models Generation for Mathematical Concept Answering Sciety Investigating Knowledge Graphs as Structured External Memory to Enhance Large Language Models’ Generation for Mathematical Concept Answering ↩
Title RAG LLMs are Not Safer A Safety Analysis of Retrieval Augmented Generation for Large Language Models RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented ↩
Retrieval augmented generation for 10 large language models and its generalizability in assessing medical fitness Sciety Retrieval Augmented Generation for 10 Large Language Models ↩
Investigating Knowledge Graphs as Structured External Memory to Enhance Large Language Models Generation for Mathematical Concept Answering Investigating Knowledge Graphs as Structured External Memory to Enhance Large Language Models’ Generation for Mathematical Concept Answering ↩
22 Ding Y et al A Survey on RAG Meets LLMs towards retrieval augmented large language models arXiv cs CL 2024 Leveraging long context in retrieval augmented language models for ↩
Authors Yu He Ke Liyuan Jin Kabilan Elangovan Hairil Rizal Abdullah Nan Liu Alex Tiong Heng Sia Chai Rick Soh Joshua Yi Min Tung Jasmine Chiat Ling Ong Chang Fu Kuo Shao Chun Wu Vesela P Kovacheva Daniel Shu Wei Ting oRetrieval Augmented Generation for 10 Large Language Models ↩
9 Gao Y Xiong Y Gao X Jia K Pan J Bi Y Dai Y Sun J Wang H Wang H Retrieval augmented generation for large language models A survey arXiv preprint arXiv 2312 10997 2023 2 Retrieval Augmented Generation Evaluation in the Era of Large ↩
2504 18041 RAG LLMs are Not Safer A Safety Analysis of Retrieval Augmented Generation for Large Language Models RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented ↩
The study found that compared to baseline methods the KG based RAG approach can enhance the groundedness and faithfulness of both the retrieved documents and the generated context Additionally low guidance can improve student learning gains Our technical framework and analysis results contribute to advancing the application of LLMs in educational technology Investigating Knowledge Graphs as Structured External Memory to Enhance Large Language Models’ Generation for Mathematical Concept Answering ↩