LLM-generated Boolean queries for systematic reviews are unstable across seeds, and the original ChatGPT results could not be reproduced with the documented setup.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Reproducibility and Generalizability Study of Large Language Models for Query Generation
LLM-generated Boolean queries for systematic reviews are unstable across seeds, and the original ChatGPT results could not be reproduced with the documented setup.