WorldMedQA-V: a multilingual, multimodal medical examination dataset for multimodal language models evaluation Paper ā¢ 2410.12722 ā¢ Published Oct 16, 2024 ā¢ 5 ā¢ 2
Language Models are Surprisingly Fragile to Drug Names in Biomedical Benchmarks Paper ā¢ 2406.12066 ā¢ Published Jun 17, 2024 ā¢ 8 ā¢ 1