From Llama to language: prompt-engineering allows general-purpose artificial intelligence to rate narratives like expert psychologists
Findings suggest that AI could significantly reduce the time and resource burdens on clinicians and researchers using narrative rating systems like the SCORS-G. Limitations and implications for future research are discussed.
Authors
- Barry Dauphin (ORCID: https://orcid.org/0000-0001-9965-4212)
- Caleb J. Siefert (ORCID: https://orcid.org/0000-0003-2255-2845)
Institutions
- University of Michigan–Dearborn (US)
- University of Detroit Mercy (US)
Publication Details
- Journal
- Frontiers in Artificial Intelligence
- Published
- 2025-02-06
- DOI
- https://doi.org/10.3389/frai.2025.1398885
- Citations
- 5
- Primary Topic
- AI in Service Interactions
- Type
- article
- Field-Weighted Citation Impact
- 12.40