LLM predictions incorporated via a developed pipeline can safely improve RCT precision, especially when trials lack strong covariates or involve text data.
Interpreting Effect Sizes of Education Interventions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.AP 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Leveraging Large Language Models to Improve Precision in Randomized Controlled Trials
LLM predictions incorporated via a developed pipeline can safely improve RCT precision, especially when trials lack strong covariates or involve text data.