| Download | - View author's version: A friendly face: do text-to-image systems rely on stereotypes when the input is under-specified? (PDF, 6.7 MiB)
|
|---|
| Author | Search for: Fraser, Kathleen C.1; Search for: Nejadgholi, Isar1; Search for: Kiritchenko, Svetlana1 |
|---|
| Affiliation | - National Research Council of Canada. Digital Technologies
|
|---|
| Format | Text, Article |
|---|
| Conference | The AAAI-23 Workshop on Creative AI Across Modalities, February 13, 2023, Washington D.C., USA |
|---|
| Physical description | 17 p. |
|---|
| Abstract | As text-to-image systems continue to grow in popularity with the general public, questions have arisen about bias and diversity in the generated images. Here, we investigate properties of images generated in response to prompts which are visually under- specified, but contain salient social attributes (e.g., ‘a portrait of a threatening person’ versus ‘a portrait of a friendly person’). Grounding our work in social cognition theory, we find that in many cases, images contain similar demographic biases to those reported in the stereotype literature. However, trends are inconsistent across different models and further investigation is warranted. |
|---|
| Publication date | 2023-02-13 |
|---|
| Publisher | Association for the Advancement of Artificial Intelligence |
|---|
| Other version | |
|---|
| Language | English |
|---|
| Peer reviewed | No |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | e836fa19-5f19-4058-81f1-28e31e272ee0 |
|---|
| Record created | 2023-09-18 |
|---|
| Record modified | 2023-09-20 |
|---|
