AINeutralarXiv – CS AI · Mar 56/10
🧠
Benchmarking MLLM-based Web Understanding: Reasoning, Robustness and Safety
Researchers introduced WebRRSBench, a comprehensive benchmark evaluating multimodal large language models' reasoning, robustness, and safety capabilities for web understanding tasks. Testing 11 MLLMs on 3,799 QA pairs from 729 websites revealed significant gaps in compositional reasoning, UI robustness, and safety-critical action recognition.