用图库函数调用让大模型更准地解决图相关问题，减少幻觉。
Graph-Grounded LLMs: Leveraging Graphical Function Calling to Minimize LLM Hallucinations
- 通过函数调用接入图库，让大模型在图任务中落地
- 在NLGraph基准上幻觉率显著降低，数学准确性提升
- 适合需高可靠性的图推理场景，如灾后救援决策
大型语言模型（LLMs）在涉及固有图结构的任务中应用日益广泛。图结构广泛应用于自动驾驶路径规划、社交网络、场景理解及知识图谱等领域。许多看似非图任务也可通过图论有效建模。然而，当前大模型在这些任务中常出现幻觉和数学错误。为此，我们提出图基大模型（Graph-Grounded LLMs），通过函数调用集成图库，使大模型在图相关任务中具备更强的可靠性。实验表明，该方法显著降低了幻觉现象，并提升了在图任务中的数学准确性，尤其在NLGraph基准测试中表现优异。最后，我们在灾后救援场景中展示了该系统作为决策支持工具的应用价值。
原文摘要 · Abstract (English)
The adoption of Large Language Models (LLMs) is rapidly expanding across various tasks that involve inherent graphical structures. Graphs are integral to a wide range of applications, including motion planning for autonomous vehicles, social networks, scene understanding, and knowledge graphs. Many problems, even those not initially perceived as graph-based, can be effectively addressed through graph theory. However, when applied to these tasks, LLMs often encounter challenges, such as hallucinations and mathematical inaccuracies. To overcome these limitations, we propose Graph-Grounded LLMs, a system that improves LLM performance on graph-related tasks by integrating a graph library through function calls. By grounding LLMs in this manner, we demonstrate significant reductions in hallucinations and improved mathematical accuracy in solving graph-based problems, as evidenced by the performance on the NLGraph benchmark. Finally, we showcase a disaster rescue application where the Graph-Grounded LLM acts as a decision-support system.
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。