Code for the paper "Large language models help facilitate the automated synthesis of information on potential pest controllers."
Training and test sets can be found under \data-sets. This includes both the raw GPT-4 generated output, as well as the datasets where GPT-4 output is aligned with the manual labels.
Here, manual labels are saved in sheet1 and GPT-4 output is saved in sheet2. The latter is colour-coded green where the cell matches the manual label and yellow where there is a mismatch.