Table 6 Results of various statistical tests assessing the convergence between ChatGPT and linguists in Exp2, using criteria from Sprouse et al. (2013).
From: Grammaticality representation in ChatGPT as compared to linguists and laypeople
One-tailed | Two-tailed | LME | Bayes factor | |
|---|---|---|---|---|
Significant in the opposite direction | - | 7 | 2 | 7 |
Marginal in the opposite direction | - | 0 | 1 | 0 |
Non-significant in the opposite direction | - | 0 | 4 | 0 |
Non-significant in the predicted direction | 8 | 1 | 23 | 2 |
Marginal in the predicted direction | 0 | 1 | 7 | 0 |
Significant in the predicted direction | 140 | 139 | 111 | 139 |
