Automation is not evidence of efficiency
We welcome Hodgson et al. (2026) empirical evaluation of ontology-grounded large language models (LLMs) for data extraction in environmental evidence synthesis. The study makes a valuable contribution by quantifying performance across attribute types and by openly documenting where current approaches struggle.
Authors
- Sini Savilaakso (ORCID: https://orcid.org/0000-0002-8514-8105)
- Matthew Grainger (ORCID: https://orcid.org/0000-0001-8426-6495)
- Neal Haddaway
- Chris Pritchard
Institutions
- University of Helsinki (FI)
- Bangor University (GB)
- Helsinki Institute of Physics (FI)
- Norwegian Institute for Nature Research (NO)
- Nottingham Trent University (GB)
Publication Details
- Journal
- Environmental Evidence
- Published
- 2026-07-02
- DOI
- https://doi.org/10.1186/s13750-026-00388-7
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 0.00