CORE-GPT: Combining Open Access research and large language models for credible, trustworthy question answering
This addresses the issue of hallucinations and lack of credibility in AI-generated answers for researchers and users seeking reliable scientific information, though it is incremental as it builds on existing models and data sources.
The paper tackled the problem of unreliable references in GPT-based language models by introducing CORE-GPT, a platform that combines GPT models with over 32 million open access articles to provide evidence-based answers with citations, resulting in comprehensive and trustworthy answers across most scientific domains as evaluated on 100 questions.
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.