PRMU Benchmark

What is PRMU?

PRMU evaluates corpus-free multimodal unlearning of person-related knowledge in MLLMs, using textual and visual probes including adversarial evaluation and…

Released

2026-08-11

Evaluates

Factuality, General AI, Multimodal

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2608.11149

PRMU paper and code

• Paper https://arxiv.org/abs/2608.11149
• Code https://github.com/2231122/PRMU

Which sources cite PRMU?

• PRMU

Related Factuality, General AI, Multimodal benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A-Bench
• A-OKVQA
• A3S-Bench
• AARRI-Bench
• ActBench