From: Evaluating the effectiveness of large language models in abstract screening: a comparative analysis
Class label | BB2016 | Mj2021 | Me2022 | |||
---|---|---|---|---|---|---|
Excluded | Included | Excluded | Included | Excluded | Included | |
1 | 53 | 3 | 21 | 32 | 83 | 4 |
2 | 4 | 93 | 42 | 0 | 4 | 54 |
3 | 43 | 4 | 8 | 0 | 13 | 15 |
4 | – | – | 29 | 0 | – | – |