In terms of benefits, the LLM achieved a perfect score of 3.0 compared with the human output’s 2.57, although this difference approached but did not reach statistical significance ( P =.10).
← all excerpts
Transforming Informed Consent Generation Using Large Language Models: Mixed Methods Study.
2
0.1000
0.1000
The sentences
A larger sample would provide greater statistical power, enabling the detection of smaller but practically significant differences between human- and LLM-generated ICFs.