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

> Research article (Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, 2022) · cited 36× · AI/ML

**Wikidata**: [openalex:W4385573253](https://www.wikidata.org/wiki/openalex:W4385573253)  
**Source**: https://4ort.xyz/entity/dalle-2-is-seeing-double-flaws-in-word-to-concept-mapping-in-text2image-models