Leveraging Large Language Models to Improve Precision in Randomized Controlled Trials
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911728569155584 |
|---|---|
| author | Lowe, Jaylin Sales, Adam Gagnon-Bartsch, Johann A. |
| author_facet | Lowe, Jaylin Sales, Adam Gagnon-Bartsch, Johann A. |
| contents | Large language models (LLMs) are increasingly used in statistical research and applications. However,they are also notorious for unreliable or biased information. Here, we explore whether LLMs can be used to improve the precision of randomized controlled trials (RCTs) in a safe and rigorous way. Following similar work on leveraging observational data, we incorporate LLM predictions into an RCT analysis. While incorporating external predictions to improve precision is not new, the value of using LLM predictions in this manner is an open question. We develop a pipeline for best leveraging LLM predictions in this context and apply it to three different case studies. We find that these predictions can safely improve precision, particularly when the RCT lacks predictive covariates or contains covariates, such as text data, that are well-suited to LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_30157 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Leveraging Large Language Models to Improve Precision in Randomized Controlled Trials Lowe, Jaylin Sales, Adam Gagnon-Bartsch, Johann A. Applications Large language models (LLMs) are increasingly used in statistical research and applications. However,they are also notorious for unreliable or biased information. Here, we explore whether LLMs can be used to improve the precision of randomized controlled trials (RCTs) in a safe and rigorous way. Following similar work on leveraging observational data, we incorporate LLM predictions into an RCT analysis. While incorporating external predictions to improve precision is not new, the value of using LLM predictions in this manner is an open question. We develop a pipeline for best leveraging LLM predictions in this context and apply it to three different case studies. We find that these predictions can safely improve precision, particularly when the RCT lacks predictive covariates or contains covariates, such as text data, that are well-suited to LLMs. |
| title | Leveraging Large Language Models to Improve Precision in Randomized Controlled Trials |
| topic | Applications |
| url | https://arxiv.org/abs/2605.30157 |