This research delved into GPT-4 and Kimi, two Large Language Models (LLMs), for systematic reviews. We evaluated their performance by comparing LLM-generated codes with human-generated codes from a peer-reviewed systematic review on assessment. Our findings suggested that the performance of LLMs fluctuates by data volume and question complexity for systematic reviews.
@article{arxiv.2504.20276,
title = {Enhancing Systematic Reviews with Large Language Models: Using GPT-4 and Kimi},
author = {Dandan Chen Kaptur and Yue Huang and Xuejun Ryan Ji and Yanhui Guo and Bradley Kaptur},
journal= {arXiv preprint arXiv:2504.20276},
year = {2025}
}
Comments
13 pages, Paper presented at the National Council on Measurement in Education (NCME) Conference, Denver, Colorado, in April 2025