Skip to main content
. 2023 Oct 30;4(12):100865. doi: 10.1016/j.patter.2023.100865

Table 3.

Validation for LLM-assisted functional similarity

Accuracy Precision Recall Correct reasoning
Functional similarity (n = 100) 0.95 0.94 0.96 0.91

Patent summarization labels were fed into GPT-4 alongside labels for the query, and the model was prompted to determine if the two sets of labels describe molecules with similar functionality. Manual validation was performed on 100 molecules randomly selected from the 27 CheSS searches’ top 250 results.