用超图增强LLM，更好理解结构化数据中的关系。
HyperG: Hypergraph-Enhanced LLMs for Structured Knowledge
- 构建超图捕捉数据间复杂结构关系
- 通过生成式补全稀疏数据，提升信息完整性
- 适合需要处理网页等结构化知识的场景
大量领域知识以结构化形式存储，如通过HTML组织的网络数据。大语言模型（LLMs）需充分理解此类信息，以拓展在各类实际下游任务中的应用。现有方法主要分为序列化和操作类两种，均难以完整捕捉结构关系并有效处理稀疏数据。为此，我们提出HyperG——一种基于超图的生成框架，旨在增强LLMs对结构化知识的处理能力。具体而言，HyperG首先利用LLMs的生成能力，为稀疏数据注入上下文信息，并引入提示感知超图学习（PHL）网络，编码增强后的信息与数据内部复杂的结构关系。为验证HyperG的有效性与泛化能力，我们在两个需依赖结构化知识的下游任务上进行了广泛实验。
原文摘要 · Abstract (English)
Given that substantial amounts of domain-specific knowledge are stored in structured formats, such as web data organized through HTML, Large Language Models (LLMs) are expected to fully comprehend this structured information to broaden their applications in various real-world downstream tasks. Current approaches for applying LLMs to structured data fall into two main categories: serialization-based and operation-based methods. Both approaches, whether relying on serialization or using SQL-like operations as an intermediary, encounter difficulties in fully capturing structural relationships and effectively handling sparse data. To address these unique characteristics of structured data, we propose HyperG, a hypergraph-based generation framework aimed at enhancing LLMs' ability to process structured knowledge. Specifically, HyperG first augment sparse data with contextual information, leveraging the generative power of LLMs, and incorporate a prompt-attentive hypergraph learning (PHL) network to encode both the augmented information and the intricate structural relationships within the data. To validate the effectiveness and generalization of HyperG, we conduct extensive experiments across two different downstream tasks requiring structured knowledge.
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。