arXiv 2503.109412025-03-13cs.AIcs.LGcs.RO

图扎根大语言模型：利用图形化函数调用最小化 LLM 幻觉

Graph-Grounded LLMs: Leveraging Graphical Function Calling to Minimize LLM Hallucinations

Honda Research Institute（本田研究所）

Piyush Gupta, Sangjae Bae, David Isele

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出 Graph-Grounded LLMs，通过函数调用接入图库为 LLM 提供图结构扎根，以减少图任务中的幻觉和数学错误，并在 NLGraph 及灾难救援场景中验证其效果。

摘要：

大语言模型（LLM）在各种涉及固有图形结构的任务中的应用正在迅速扩展。图是众多应用不可或缺的一部分，包括自动驾驶车辆的运动规划、社交网络、场景理解和知识图谱。许多问题，即使最初并不被视为基于图的问题，也可以通过图论得到有效解决。然而，当应用于这些任务时，LLM 经常遇到挑战，例如幻觉和数学上的不准确性。为了克服这些限制，我们提出了 Graph-Grounded LLMs，这是一个通过函数调用集成图库来提升 LLM 在图相关任务上性能的系统。通过以这种方式为 LLM 提供扎根基础，我们证明了在解决基于图的问题时幻觉显著减少、数学准确性得到提高，NLGraph 基准上的性能即为明证。最后，我们展示了一个灾难救援应用，其中 Graph-Grounded LLM 充当决策支持系统。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

AI总结：

摘要：

英文摘要：

相关论文