Research case
Can GPT-4 replace humans in systematic reviews? (Khraisha et al., Research Synthesis Methods 2024)
A preregistered study tests GPT-4 for title/abstract screening, full-text review and data extraction across languages and literature types.
What is reported
After accounting for chance agreement and imbalance, performance ranged from none to moderate in many settings; full-text screening with reliable prompts performed much better.
Before you use it
The authors urge substantial caution; good results depended on prompt quality and did not hold across stages or languages.
Sources and review
Source checked · Not tested by this site
Checked the public abstract and bibliographic record. Results describe the authors' study, not a replication by this site.
License and reuse
No license has been recorded. Check the source’s license before reusing code, models or data.
A license note is not a license audit. Open source does not guarantee free hosting, model access or commercial reuse.