New benchmark tests MLLMs on repairing toxic molecules

Researchers have introduced ToxiMol, a new benchmark designed to evaluate how well multimodal large language models (MLLMs) can repair toxic molecules. This benchmark includes a dataset of 660 toxic molecules across 11 tasks and an automated evaluation framework called ToxiEval. Initial experiments with 43 MLLMs show that while current models struggle with this task, they are beginning to exhibit promising abilities in understanding toxicity and performing structure-aware edits. AI

影响 Establishes a new evaluation standard for MLLMs in molecular toxicity repair, potentially guiding future drug development research.

排序理由 The cluster contains an academic paper introducing a new benchmark and evaluation framework for MLLMs. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

• Fei Lin
• MLLMs
• ToxiEval
• ToxiMol

• 论文
• 安全

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →