Leveraging LLMs in Scholarly Knowledge Graph Question Answering

TL;DR

This paper introduces a novel method for scholarly knowledge graph question answering that combines BERT-based similarity, few-shot prompting of large language models, and SPARQL query generation to accurately answer bibliographic questions.

Contribution

It proposes a new approach that leverages LLMs with few-shot learning and similarity retrieval for improved scholarly KGQA performance.

Findings

Achieved 99.0% F1 score on SciQA benchmark.

Effectively combines BERT similarity with LLM prompting for KGQA.

Demonstrates high accuracy in scholarly question answering tasks.

Abstract

This paper presents a scholarly Knowledge Graph Question Answering (KGQA) that answers bibliographic natural language questions by leveraging a large language model (LLM) in a few-shot manner. The model initially identifies the top-n similar training questions related to a given test question via a BERT-based sentence encoder and retrieves their corresponding SPARQL. Using the top-n similar question-SPARQL pairs as an example and the test question creates a prompt. Then pass the prompt to the LLM and generate a SPARQL. Finally, runs the SPARQL against the underlying KG - ORKG (Open Research KG) endpoint and returns an answer. Our system achieves an F1 score of 99.0%, on SciQA - one of the Scholarly-QALD-23 challenge benchmarks.