用概念元关系增强大模型理解力，解决术语模糊问题
LGM: Enhancing Large Language Models with Conceptual Meta-Relations and Iterative Retrieval
- 从自然语言提取继承、别名、组合等概念元关系
- 动态检索关联描述，使模型在长文本中保持准确响应
- 无需截断文本，适合处理任意长度输入的任务
大语言模型虽具备较强语义理解能力，但在用户指令涉及模糊或概念错位术语时表现不佳。本文提出语言图模型（LGM），通过从自然语言中提取继承、别名和组合等概念元关系来增强概念清晰度，并引入反思机制验证这些关系。借助概念迭代检索算法，将相关关系与描述动态供给大模型，提升其对概念的解析与生成能力。与依赖扩展上下文窗口的传统检索增强生成方法不同，该方法可处理任意长度文本而无需截断。在标准基准测试中，LGM始终优于现有RAG基线。
原文摘要 · Abstract (English)
Large language models (LLMs) exhibit strong semantic understanding, yet struggle when user instructions involve ambiguous or conceptually misaligned terms. We propose the Language Graph Model (LGM) to enhance conceptual clarity by extracting meta-relations-inheritance, alias, and composition-from natural language. The model further employs a reflection mechanism to validate these meta-relations. Leveraging a Concept Iterative Retrieval Algorithm, these relations and related descriptions are dynamically supplied to the LLM, improving its ability to interpret concepts and generate accurate responses. Unlike conventional Retrieval-Augmented Generation (RAG) approaches that rely on extended context windows, our method enables large language models to process texts of any length without the need for truncation. Experiments on standard benchmarks demonstrate that the LGM consistently outperforms existing RAG baselines.
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。