Table 1.

Representativeness–direction differentiability using racialized surnames in ChatGPT and SBERT.

AI ModelCategoryWarmthCompetence
DirectionRepresentativenessDirectionRepresentativeness
ChatGPTAsian0.639a0.21a0.776a0.34ab
Hispanic0.828b0.36b0.928b0.31a
White0.947b0.41b0.884b0.43b
SBERTAsian−0.295a0.118ab0.522a0.040ab
Hispanic−0.494a0.081a0.442a0.027a
White−0.536a0.147b0.064a0.066b
AI ModelCategoryWarmthCompetence
DirectionRepresentativenessDirectionRepresentativeness
ChatGPTAsian0.639a0.21a0.776a0.34ab
Hispanic0.828b0.36b0.928b0.31a
White0.947b0.41b0.884b0.43b
SBERTAsian−0.295a0.118ab0.522a0.040ab
Hispanic−0.494a0.081a0.442a0.027a
White−0.536a0.147b0.064a0.066b

Within AI model, for each column, values with the same superscript are not significantly different (P > 0.05).

Table 1.

Representativeness–direction differentiability using racialized surnames in ChatGPT and SBERT.

AI ModelCategoryWarmthCompetence
DirectionRepresentativenessDirectionRepresentativeness
ChatGPTAsian0.639a0.21a0.776a0.34ab
Hispanic0.828b0.36b0.928b0.31a
White0.947b0.41b0.884b0.43b
SBERTAsian−0.295a0.118ab0.522a0.040ab
Hispanic−0.494a0.081a0.442a0.027a
White−0.536a0.147b0.064a0.066b
AI ModelCategoryWarmthCompetence
DirectionRepresentativenessDirectionRepresentativeness
ChatGPTAsian0.639a0.21a0.776a0.34ab
Hispanic0.828b0.36b0.928b0.31a
White0.947b0.41b0.884b0.43b
SBERTAsian−0.295a0.118ab0.522a0.040ab
Hispanic−0.494a0.081a0.442a0.027a
White−0.536a0.147b0.064a0.066b

Within AI model, for each column, values with the same superscript are not significantly different (P > 0.05).

Close
This Feature Is Available To Subscribers Only

Sign In or Create an Account

Close

This PDF is available to Subscribers Only

View Article Abstract & Purchase Options

For full access to this pdf, sign in to an existing account, or purchase an annual subscription.

Close