Answers are grounded in this paper and cite their sources.
Prototype test harness evaluates retrieval-augmented generation systems in humanities research, suggesting new software engineering principles for better outcomes.
This paper describes a prototype test harness that has been developed to evaluate the use of large language model retrieval-augmented generation systems for humanities and social science research, with an emphasis on collections held in the galleries, libraries, archives and museum sector. We propose the development of new modes of research software engineering oriented towards the values and principles of those communities, and rigorous modes of software testing grounded in industry best practices.
No takes yet. Share an insight, caveat, or question.
Smithies et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: