Skip to main content
. 2023 Nov 22;13:20512. doi: 10.1038/s41598-023-46995-z

Table 5.

Results of the correlation analysis with Pearson correlation coefficient and obtained p-value given in the brackets along with p-value obtained from the Mann–Whitney U test comparing the values of the discrimination power index for correct and incorrect answers for temperature parameter equal to 0.

S22 A22 S23
Polish
 GPT-3.5
  Pearson correlation coefficient (p-value) − 0.124 (0.083 ns) − 0.243 (< 0.001***) − 0.327 (< 0.001***)
  p-value from Mann–Whitney U test 0.053 ns  < 0.001***  < 0.001***
  Cohen’s d 0.251 0.499 0.690
 GPT-4
  Pearson correlation coefficient (p-value) − 0.029 (0.690 ns) − 0.249 (< 0.001***) − 0.185 (0.010**)
  p-value from Mann–Whitney U test 0.410 ns 0.001** 0.031*
  Cohen’s d 0.067 0.661 0.482
English
 GPT-3.5
  Pearson correlation coefficient (p-value) − 0.103 (0.150 ns) − 0.176 (0.013*) − 0.182 (0.011*)
  p-value from Mann–Whitney U test 0.090 ns 0.005** 0.009**
  Cohen’s d 0.210 0.363 0.394
 GPT-4
  Pearson correlation coefficient (p-value) − 0.011 (0.877 ns) − 0.146 (0.041*) − 0.140 (0.051 ns)
  p-value from Mann–Whitney U test 0.704 ns 0.072 ns 0.137 ns
  Cohen’s d 0.026 0.368 0.380