Microstructures and Accuracy of Graph Recall by Large Language Models

arXiv:2402.11821v1 Announce Type: new
Abstract: Graphs data is crucial for many applications, and much of it exists in the relations described in textual format. As a result, being able to accurately recall and encode a graph described in earlier text is a basic yet pivotal ability that LLMs need to demonstrate if they are to perform reasoning tasks that involve graph-structured information. Human performance at graph recall by has been studied by cognitive scientists for decades, and has been found …

abstract accuracy applications arxiv basic cs.cl cs.ir cs.lg cs.si data encode format graph graphs language language models large language large language models llms pivotal recall relations text textual type