Large Language Models with Human-In-The-Loop Validation for Systematic Review Data Extraction
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910792139407360 |
|---|---|
| author | Schroeder, Noah L. Jaldi, Chris Davis Zhang, Shan |
| author_facet | Schroeder, Noah L. Jaldi, Chris Davis Zhang, Shan |
| contents | Systematic reviews are time-consuming endeavors. Historically speaking, knowledgeable humans have had to screen and extract data from studies before it can be analyzed. However, large language models (LLMs) hold promise to greatly accelerate this process. After a pilot study which showed great promise, we investigated the use of freely available LLMs for extracting data for systematic reviews. Using three different LLMs, we extracted 24 types of data, 9 explicitly stated variables and 15 derived categorical variables, from 112 studies that were included in a published scoping review. Overall we found that Gemini 1.5 Flash, Gemini 1.5 Pro, and Mistral Large 2 performed reasonably well, with 71.17%, 72.14%, and 62.43% of data extracted being consistent with human coding, respectively. While promising, these results highlight the dire need for a human-in-the-loop (HIL) process for AI-assisted data extraction. As a result, we present a free, open-source program we developed (AIDE) to facilitate user-friendly, HIL data extraction with LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_11840 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Large Language Models with Human-In-The-Loop Validation for Systematic Review Data Extraction Schroeder, Noah L. Jaldi, Chris Davis Zhang, Shan Human-Computer Interaction Systematic reviews are time-consuming endeavors. Historically speaking, knowledgeable humans have had to screen and extract data from studies before it can be analyzed. However, large language models (LLMs) hold promise to greatly accelerate this process. After a pilot study which showed great promise, we investigated the use of freely available LLMs for extracting data for systematic reviews. Using three different LLMs, we extracted 24 types of data, 9 explicitly stated variables and 15 derived categorical variables, from 112 studies that were included in a published scoping review. Overall we found that Gemini 1.5 Flash, Gemini 1.5 Pro, and Mistral Large 2 performed reasonably well, with 71.17%, 72.14%, and 62.43% of data extracted being consistent with human coding, respectively. While promising, these results highlight the dire need for a human-in-the-loop (HIL) process for AI-assisted data extraction. As a result, we present a free, open-source program we developed (AIDE) to facilitate user-friendly, HIL data extraction with LLMs. |
| title | Large Language Models with Human-In-The-Loop Validation for Systematic Review Data Extraction |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2501.11840 |