Skip to main content
. 2024 May 1;7:106. doi: 10.1038/s41746-024-01079-8

Fig. 5. Case analysis to reveal typical errors in ChatGPT outputs.

Fig. 5

a TCGA-22-4609 illustrates a typical case where the GPT model uses a false rule, which is incorrect by AJCC guideline. b Case TCGA-39-5028 shows a complex case where there exist two tumors and the GPT model only capture one of them. c Case TCGA-39-5016 reveals a case where the GPT model made a mistake for getting confused with domain terminology.