Papers with DemOgraphic

1 papers
The Factuality Tax of Diversity-Intervened Text-to-Image Generation: Benchmark and Fact-Augmented Intervention (2024.emnlp-main)

Copied to clipboard

Challenge: Prompt-based “diversity interventions” are commonly adopted to improve the diversity of Text-to-Image models depicting individuals with diverse racial or gender traits.
Approach: They propose a benchmark to quantify the trade-off between using diversity interventions and preserving demographic factuality in T2I models.
Outcome: The proposed model significantly improves the demographic factuality under diversity interventions while preserving diversity.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations