In which fields do ChatGPT 4o scores align better than citations with research quality? (2504.04464v1)

Abstract: Although citation-based indicators are widely used for research evaluation, they are not useful for recently published research, reflect only one of the three common dimensions of research quality, and have little value in some social sciences, arts and humanities. LLMs have been shown to address some of these weaknesses, with ChatGPT 4o-mini showing the most promising results, although on incomplete data. This article reports by far the largest scale evaluation of ChatGPT 4o-mini yet, and also evaluates its larger sibling ChatGPT 4o. Based on comparisons between LLM scores, averaged over 5 repetitions, and departmental average quality scores for 107,212 UK-based refereed journal articles, ChatGPT 4o is marginally better than ChatGPT 4o-mini in most of the 34 field-based Units of Assessment (UoAs) tested, although combining both gives better results than either one. ChatGPT 4o scores have a positive correlation with research quality in 33 of the 34 UoAs, with the results being statistically significant in 31. ChatGPT 4o scores had a higher correlation with research quality than long term citation rates in 21 out of 34 UoAs and a higher correlation than short term citation rates in 26 out of 34 UoAs. The main limitation is that it is not clear whether ChatGPT leverages public information about departmental research quality to cheat with its scores. In summary, the results give the first large scale evidence that ChatGPT 4o is competitive with citations as a new research quality indicator, but ChatGPT 4o-mini, which is more cost-effective.