[2605.31349] FBHM: Functional Benchmarking and Steering of VLMs for Hateful Meme Detection

Read full story on arxiv.org
Share
[2605.31349] FBHM: Functional Benchmarking and Steering of VLMs for Hateful Meme Detection
AI disclosure

Summary

Abstract page for arXiv paper 2605.31349: FBHM: Functional Benchmarking and Steering of VLMs for Hateful Meme Detection

Original reporting

Open original source
Read full article on arxiv.org