Whilst Large Language Models (LLMs) have a weak to moderate ability to score published journal articles for research quality, they have not been compared with individual expert reviewers. It is also unknown whether quality scores from ChatGPT based on PDFs can improve on those from titles and abstracts through a deeper evaluation. To address both issues, this article uses expert scores (98 internal departmental ratings for UK Unit of Assessment [UoA] 3 Allied Health Professions, 44 for UoA13 Architecture, and 58 library and information science articles from UoA34), comparing them against ChatGPT-5.4 scores from both title/abstract and PDF inputs. For UoA3, individual reviewer scores were also compared against each other and ChatGPT-5.4. The rank correlations with expert scores are almost all statistically significantly positive, but differences between the correlations are mostly not, despite weakly suggesting that ChatGPT-5.4 can be more reliable than individual reviewers for UoA3. Moreover, whilst ChatGPT-5.4 provides more detailed evaluations of PDFs than of titles/abstracts, its score predictions do not seem to improve. Thus, whilst the results broadly confirm the value of ChatGPT scores for ranking academic documents, its apparently deeper evaluative comments on PDFs are misleading in the sense of not translating to improved score predictions.

翻译：暂无翻译