Evaluation topic

Multimodal

Evaluations requiring or assessing combinations of text, images, audio or other modalities.

8 records are tagged here. Inclusion does not establish construct equivalence, completeness, or comparability.

• CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language ModelsManish Bhatt, Sahana Chennabasappa, Cyrus Nikolaidis et al.
• DocVQA: A Dataset for VQA on Document ImagesMinesh Mathew, Dimosthenis Karatzas, C. V. Jawahar
• MathVista: Visual Math Problem-SolvingPan Lu, Hritik Bansal, Tony Xia et al.
• MM-SafetyBenchMM-SafetyBench paper authors
• Mmmu Multiple ChoiceXiang Yue, Yuansheng Ni, Kai Zhang et al.
• Mmmu OpenXiang Yue, Yuansheng Ni, Kai Zhang et al.
• VisualWebArenaCarnegie Mellon University and the VisualWebArena paper authors
• VQA-RAD: Visual Question Answering for RadiologyAssociated paper authors