How Proficient Are Large Language Models in Formal Languages? An In-Depth Insight for Knowledge Base Question Answering

arXiv:2401.05777v2 Announce Type: replace
Abstract: Knowledge Base Question Answering (KBQA) aims to answer natural language questions based on facts in knowledge bases. A typical approach to KBQA is semantic parsing, which translates a question into an executable logical form in a formal language. Recent works leverage the capabilities of large language models (LLMs) for logical form generation to improve performance. However, although it is validated that LLMs are capable of solving some KBQA problems, there has been little discussion on …

abstract arxiv cs.cl facts form insight knowledge knowledge base language language models languages large language large language models natural natural language parsing question question answering questions replace semantic type