Enhancing Systematic Reviews with Large Language Models: Using GPT-4 and Kimi
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913812092813312 |
|---|---|
| author | Kaptur, Dandan Chen Huang, Yue Ji, Xuejun Ryan Guo, Yanhui Kaptur, Bradley |
| author_facet | Kaptur, Dandan Chen Huang, Yue Ji, Xuejun Ryan Guo, Yanhui Kaptur, Bradley |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_20276 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Systematic Reviews with Large Language Models: Using GPT-4 and Kimi Kaptur, Dandan Chen Huang, Yue Ji, Xuejun Ryan Guo, Yanhui Kaptur, Bradley Computation and Language Applications 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. |
| title | Enhancing Systematic Reviews with Large Language Models: Using GPT-4 and Kimi |
| topic | Computation and Language Applications |
| url | https://arxiv.org/abs/2504.20276 |