MIRAGE: Multi-model Interface for Reviewing and Auditing Generative Text-to-Image AI
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916665642450944 |
|---|---|
| author | Maldaner, Matheus Kunzler Deng, Wesley Hanwen Hong, Jason Holstein, Ken Eslami, Motahhare |
| author_facet | Maldaner, Matheus Kunzler Deng, Wesley Hanwen Hong, Jason Holstein, Ken Eslami, Motahhare |
| contents | While generative AI systems have gained popularity in diverse applications, their potential to produce harmful outputs limits their trustworthiness and usability in different applications. Recent years have seen growing interest in engaging diverse AI users in auditing generative AI that might impact their lives. To this end, we propose MIRAGE as a web-based tool where AI users can compare outputs from multiple AI text-to-image (T2I) models by auditing AI-generated images, and report their findings in a structured way. We used MIRAGE to conduct a preliminary user study with five participants and found that MIRAGE users could leverage their own lived experiences and identities to surface previously unnoticed details around harmful biases when reviewing multiple T2I models' outputs compared to reviewing only one. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_19252 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MIRAGE: Multi-model Interface for Reviewing and Auditing Generative Text-to-Image AI Maldaner, Matheus Kunzler Deng, Wesley Hanwen Hong, Jason Holstein, Ken Eslami, Motahhare Human-Computer Interaction While generative AI systems have gained popularity in diverse applications, their potential to produce harmful outputs limits their trustworthiness and usability in different applications. Recent years have seen growing interest in engaging diverse AI users in auditing generative AI that might impact their lives. To this end, we propose MIRAGE as a web-based tool where AI users can compare outputs from multiple AI text-to-image (T2I) models by auditing AI-generated images, and report their findings in a structured way. We used MIRAGE to conduct a preliminary user study with five participants and found that MIRAGE users could leverage their own lived experiences and identities to surface previously unnoticed details around harmful biases when reviewing multiple T2I models' outputs compared to reviewing only one. |
| title | MIRAGE: Multi-model Interface for Reviewing and Auditing Generative Text-to-Image AI |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2503.19252 |