将知识图谱嵌入大模型，实现高效精准的符号推理
Injecting Knowledge Graphs into Large Language Models
- 用知识图谱嵌入技术将结构化知识以令牌形式注入模型输入
- 在多个数据集上超越现有基线，平衡了准确率与计算效率
- 不依赖特定模型，适配任意大语言模型，资源开销小
将知识图谱（KG）中的结构化知识融入大型语言模型（LLMs）仍是符号推理的关键挑战。现有方法主要依赖提示工程或微调，易丢失结构信息或带来高计算成本。基于近期将图嵌入作为令牌集成到LLM输入的编码技术，本文将其拓展至知识图谱领域，利用知识图谱嵌入（KGE）模型实现图感知推理。该方法具有模型无关性、资源高效性，并兼容任意LLM。在合成及真实世界数据集上的广泛实验表明，该方法在推理性能上优于已有基线，且在准确率与效率之间实现了最佳平衡。
原文摘要 · Abstract (English)
Integrating structured knowledge from Knowledge Graphs (KGs) into Large Language Models (LLMs) remains a key challenge for symbolic reasoning. Existing methods mainly rely on prompt engineering or fine-tuning, which lose structural fidelity or incur high computational costs. Building on recent encoding techniques which integrate graph embeddings within the LLM input as tokens, we extend this paradigm to the KG domain by leveraging Knowledge Graph Embedding (KGE) models, thus enabling graph-aware reasoning. Our approach is model-agnostic, resource-efficient, and compatible with any LLMs. Extensive experimentation on synthetic and real-world datasets shows that our method improves reasoning performance over established baselines, further achieving the best trade-off in terms of accuracy and efficiency against state-of-the-art LLMs.
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。