CORE-GPT: Combining Open Access Research and Large Language Models for Credible, Trustworthy Question Answering

Pride, David; Cancellieri, Matteo and Knoth, Petr (2023). CORE-GPT: Combining Open Access Research and Large Language Models for Credible, Trustworthy Question Answering. In: Linking Theory and Practice of Digital Libraries. TPDL 2023. Lecture Notes in Computer Science, vol 14241. (Alonso, Omar; Cousijn, Helena; Silvello, Gianmaria; Marrero, Mónica; Teixeira Lopes, Carla and Marchesin, Stefano eds.), pp. 146–159.

DOI: https://doi.org/10.1007/978-3-031-43849-3_13

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 (https://core.ac.uk). 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 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.