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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gupta, Piyush, Bae, Sangjae, Isele, David
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915197551116288
author Gupta, Piyush
Bae, Sangjae
Isele, David
author_facet Gupta, Piyush
Bae, Sangjae
Isele, David
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_10941
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Graph-Grounded LLMs: Leveraging Graphical Function Calling to Minimize LLM Hallucinations
Gupta, Piyush
Bae, Sangjae
Isele, David
Artificial Intelligence
Machine Learning
Robotics
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.
title Graph-Grounded LLMs: Leveraging Graphical Function Calling to Minimize LLM Hallucinations
topic Artificial Intelligence
Machine Learning
Robotics
url https://arxiv.org/abs/2503.10941