CORE-GPT: Combining Open Access research and large language models for credible, trustworthy question answering

TL;DR

CORE-GPT is a new question-answering system that combines large language models with a vast open access scientific article database to provide evidence-based, trustworthy answers with citations, addressing hallucination issues.

Contribution

The paper introduces CORE-GPT, a platform integrating GPT models with 32 million open access articles to enhance answer credibility and citation accuracy.

Findings

CORE-GPT provides trustworthy, evidence-based answers with relevant citations.

The system effectively covers multiple scientific domains.

It reduces hallucinations compared to standard GPT models.

Abstract

In this paper, we present CORE-GPT, a novel question-answering platform that combines GPT-based language models and more than 32 million full-text open access scientific articles from CORE. We first demonstrate that GPT3.5 and GPT4 cannot be relied upon to provide references or citations for generated text. We then introduce CORE-GPT which delivers evidence-based answers to questions, along with citations and links to the cited papers, greatly increasing the trustworthiness of the answers and reducing the risk of hallucinations. CORE-GPT's performance was evaluated on a dataset of 100 questions covering the top 20 scientific domains in CORE, resulting in 100 answers and links to 500 relevant articles. The quality of the provided answers and and relevance of the links were assessed by two annotators. Our results demonstrate that CORE-GPT can produce comprehensive and trustworthy answers across the majority of scientific domains, complete with links to genuine, relevant scientific articles.