inFaaa/Evolver

[COLING 2025🔥] Evolver: Chain-of-Evolution Prompting to Boost Large Multimodal Models for Hateful Meme Detection

22
/ 100
Experimental

This project helps social media content moderators, online community managers, or platform safety analysts identify hateful memes more accurately. It takes an image-text meme and a definition of hatefulness as input. It then outputs a classification of whether the meme is hateful, improving upon existing large multimodal models.

No commits in the last 6 months.

Use this if you need a more effective way to detect hateful content in memes, especially when existing AI tools struggle with nuanced cases.

Not ideal if you're looking for a simple plug-and-play solution without needing to configure or run Python scripts.

content-moderation online-safety social-media-analysis harmful-content-detection meme-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

17

Forks

Language

Python

License

Apache-2.0

Last pushed

Jan 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/inFaaa/Evolver"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.