NUWA 风险评测 · 评测基准
Virology Capabilities Test (VCT): A Multimodal Virology Q&A Benchmark
NUWA 研究解读 · 独立复核待完成
NUWA Research Note
研究问题研究设计与假设来源发现NUWA 解读局限与相反证据研究与决策意义机构与角色原始资源模型辅助整理 · 选读原始全文或官方文章中的相关章节；尚未完成逐章节审计。
研究速读
NUWA 解读：专家题表现不是已证明的湿实验用户增益。
研究问题
模型回答专家编写的病毒学问题表现如何？
研究设计与假设
322道多模态题采用多选全对计分，人类比较限于各自专业范围。
来源发现
o3为43.8%，可联网专家均值22.1%。
论文另分析答案集合差异和替代格式（§5.1）。
NUWA 解读
NUWA 解读：专家题表现不是已证明的湿实验用户增益。
局限与相反证据
专家可能对答案有分歧，具身与协作隐性知识覆盖有限（§6、附录A3）。
研究与决策意义
模型建议：保留专业匹配和计分格式，仅作为非操作性能力证据。
精确来源位置
- Virology Capabilities Test (VCT): A Multimodal Virology Q&A Benchmark · AbstractSelected original resource https://arxiv.org/html/2504.16137v2; sha256:3b0bc61ab556258ca26318138a0ac00dbfb59bb8d3318a8038b71a6788be0d99; archived source capture; exact capture time not independently established
- Virology Capabilities Test (VCT): A Multimodal Virology Q&A Benchmark · §5.1 SetupSelected original resource https://arxiv.org/html/2504.16137v2; sha256:3b0bc61ab556258ca26318138a0ac00dbfb59bb8d3318a8038b71a6788be0d99; archived source capture; exact capture time not independently established
- Virology Capabilities Test (VCT): A Multimodal Virology Q&A Benchmark · §6 DiscussionSelected original resource https://arxiv.org/html/2504.16137v2; sha256:3b0bc61ab556258ca26318138a0ac00dbfb59bb8d3318a8038b71a6788be0d99; archived source capture; exact capture time not independently established
- Virology Capabilities Test (VCT): A Multimodal Virology Q&A Benchmark · Appendix A3 Limitations of This WorkSelected original resource https://arxiv.org/html/2504.16137v2; sha256:3b0bc61ab556258ca26318138a0ac00dbfb59bb8d3318a8038b71a6788be0d99; archived source capture; exact capture time not independently established
来源核查、数据提取、编辑批准与实验复现分别记录。 方法说明 →
机构与角色
作者 (9)
Jasper Götting · Pedro Medeiros · Jon G Sanders · Nathaniel Li · Long Phan · Karam Elabd · Lennart Justen · Dan Hendrycks · Seth Donoughe
评测协议
引用与复用
引用研究发现时请引用原始出版物；引用 NUWA 的整理与解释时，单独引用本站记录及对应快照。
原始出版物 · BibTeX
@misc{vct,
title = {Virology Capabilities Test (VCT): A Multimodal Virology Q\&A Benchmark},
url = {https://arxiv.org/abs/2504.16137v2},
author = {Jasper Götting and Pedro Medeiros and Jon G Sanders and Nathaniel Li and Long Phan and Karam Elabd and Lennart Justen and Dan Hendrycks and Seth Donoughe},
year = {2025},
date = {2025-04-21},
version = {arXiv:2504.16137v2},
note = {arXiv:2504.16137v2}
}
NUWA 记录 · BibTeX
@misc{vct-nuwa,
title = {Virology Capabilities Test (VCT): A Multimodal Virology Q\&A Benchmark — NUWA research record},
url = {https://whitzard.tech/nuwa/whitzard-index/work/vct/},
version = {2026-10-29.1},
organization = {NUWA Frontier AI Safety Lab},
howpublished = {Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--vct.json},
note = {NUWA research note. Source-reading scope and independent review status are stated on the record. Snapshot 2026-10-29.1. Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--vct.json.}
}
证据快照 2026-10-29.1 · 索引更新 · RSS
参考文献
- [1] Jasper Götting a, Pedro Medeiros a 等. Virology Capabilities Test (VCT): A Multimodal Virology Q&A Benchmark. 2025-04-29. v2 [arXiv]; Author affiliations on the original paper title page; Abstract; §5.1 Setup