DALLE-2 is Seeing Double: Flaws in Word-to-Concept Mapping in Text2Image Models

Royi Rassin, Shauli Ravfogel, Yoav Goldberg

BibTeX
@inproceedings{rassin2022dalle,
  author = {Royi Rassin and Shauli Ravfogel and Yoav Goldberg},
  title = {{DALLE-2 is Seeing Double: Flaws in Word-to-Concept Mapping in Text2Image Models}},
  booktitle = {BlackboxNLP @ EMNLP},
  year = {2022},
  doi = {10.18653/v1/2022.blackboxnlp-1.28},
}
Figure