Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning

arXiv:2310.01061v2 Announce Type: replace
Abstract: Large language models (LLMs) have demonstrated impressive reasoning abilities in complex tasks. However, they lack up-to-date knowledge and experience hallucinations during reasoning, which can lead to incorrect reasoning processes and diminish their performance and trustworthiness. Knowledge graphs (KGs), which capture vast amounts of facts in a structured format, offer a reliable source of knowledge for reasoning. Nevertheless, existing KG-based LLM reasoning methods only treat KGs as factual knowledge bases and overlook the importance of their …

abstract arxiv cs.ai cs.cl experience facts graphs hallucinations knowledge knowledge graphs language language model language models large language large language model large language models llms performance processes reasoning tasks type vast