用知识增强的LLM提升文献检索效率，助力系统综述
NeuroLit Navigator: A Neurosymbolic Approach to Scholarly Article Searches for Systematic Reviews
- 结合医学术语库与领域LLM，优化检索关键词生成
- 实测将初筛文献时间缩短90%，显著提效
- 适合图书馆员与科研人员做系统综述时快速定位文献
大语言模型（LLMs）在教育等领域已展现潜力，但在系统综述（SRs）中仍存在专业词汇覆盖不足、领域推理能力弱及生成虚假信息等问题。现有工具多依赖传统NLP方法，难以有效应对。为此，我们提出NeuroLit Navigator，融合领域专用LLM与结构化知识源（如MeSH和UMLS），提升查询构建能力、扩展检索词汇并深化搜索范围，实现更精准的文献发现。该系统已在多所大学部署，经十余名图书馆员测试，使初始文献筛选时间减少90%。尽管初步结果相关性与质量存在差异，但显著提升了检索过程的可复现性，展现出支持系统综述工作的巨大潜力。
原文摘要 · Abstract (English)
The introduction of Large Language Models (LLMs) has significantly impacted various fields, including education, for example, by enabling the creation of personalized learning materials. However, their use in Systematic Reviews (SRs) reveals limitations such as restricted access to specialized vocabularies, lack of domain-specific reasoning, and a tendency to generate inaccurate information. Existing SR tools often rely on traditional NLP methods and fail to address these issues adequately. To overcome these challenges, we developed the ``NeuroLit Navigator,'' a system that combines domain-specific LLMs with structured knowledge sources like Medical Subject Headings (MeSH) and the Unified Medical Language System (UMLS). This integration enhances query formulation, expands search vocabularies, and deepens search scopes, enabling more precise searches. Deployed in multiple universities and tested by over a dozen librarians, the NeuroLit Navigator has reduced the time required for initial literature searches by 90\%. Despite this efficiency, the initial set of articles retrieved can vary in relevance and quality. Nonetheless, the system has greatly improved the reproducibility of search results, demonstrating its potential to support librarians in the SR process.
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。