Can ChatGPT be a good follower of academic paradigms? Research quality evaluations in conflicting areas of sociology

TL;DR

This study investigates whether ChatGPT can objectively evaluate academic papers across conflicting sociology paradigms, revealing that it favors aligned paradigms and highlighting the importance of neutral instructions for fair research assessment.

Contribution

It demonstrates that LLMs like ChatGPT can be prompted to show bias towards specific academic paradigms, emphasizing the need for careful prompt design in research evaluations.

Findings

ChatGPT scores higher when evaluating articles aligned with its prompted paradigm.

Evaluations by opposing paradigm prompts result in lower scores for those articles.

Follower prompts cause only slight bias, but opposing prompts create significant disadvantages.

Abstract

Purpose: It has become increasingly likely that Large Language Models (LLMs) will be used to score the quality of academic publications to support research assessment goals in the future. This may cause problems for fields with competing paradigms since there is a risk that one may be favoured, causing long term harm to the reputation of the other. Design/methodology/approach: To test whether this is plausible, this article uses 17 ChatGPTs to evaluate up to 100 journal articles from each of eight pairs of competing sociology paradigms (1490 altogether). Each article was assessed by prompting ChatGPT to take one of five roles: paradigm follower, opponent, antagonistic follower, antagonistic opponent, or neutral. Findings: Articles were scored highest by ChatGPT when it followed the aligning paradigm, and lowest when it was told to devalue it and to follow the opposing paradigm. Broadly similar patterns occurred for most of the paradigm pairs. Follower ChatGPTs displayed only a small amount of favouritism compared to neutral ChatGPTs, but articles evaluated by an opposing paradigm ChatGPT had a substantial disadvantage. Research limitations: The data covers a single field and LLM. Practical implications: The results confirm that LLM instructions for research evaluation should be carefully designed to ensure that they are paradigm-neutral to avoid accidentally resolving conflicts between paradigms on a technicality by devaluing one side's contributions. Originality/value: This is the first demonstration that LLMs can be prompted to show a partiality for academic paradigms.