风险评测 · 评测基准

LAB-Bench Measuring Capabilities of Language Models for Biology Research

NUWA 研究解读 · 独立复核待完成

首次发表: 2024-07-14来源核验: 2026-10-25

原始来源 ↗引用本记录 ↓化生放核 →

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：格式真实性及人类覆盖决定比较含义。

研究问题

生物基准能否从教科书知识转向实际研究支持技能？

研究设计与假设

LAB-Bench含逾2,400道选择题，覆盖文献、图表、数据库等研究支持任务，配部分专家基线。

来源发现

构造中发现专家修改模型提议题目有帮助。

因招募困难，人类专家未覆盖全题集（§3.5）。

NUWA 解读

NUWA 解读：格式真实性及人类覆盖决定比较含义。

局限与相反证据

作者不声称全面覆盖生物，无工具选择题不能确立真实实验执行或增益。

研究与决策意义

模型建议：保留子任务、工具及真实人类覆盖，不提取操作性生物内容。

精确来源位置

LAB-Bench · AbstractSelected original resource https://arxiv.org/html/2407.10362; sha256:fb4550ba8cc17a4ffb2f30a3e9f1fe78a538a5c1d3508550942723e506ffe2c8; archived source capture; exact capture time not independently established
LAB-Bench · §2.1 Dataset description and constructionSelected original resource https://arxiv.org/html/2407.10362; sha256:fb4550ba8cc17a4ffb2f30a3e9f1fe78a538a5c1d3508550942723e506ffe2c8; archived source capture; exact capture time not independently established
LAB-Bench · §3 Discussion and LimitationsSelected original resource https://arxiv.org/html/2407.10362; sha256:fb4550ba8cc17a4ffb2f30a3e9f1fe78a538a5c1d3508550942723e506ffe2c8; archived source capture; exact capture time not independently established
LAB-Bench · §3.5 Limitations in human evaluationSelected original resource https://arxiv.org/html/2407.10362; sha256:fb4550ba8cc17a4ffb2f30a3e9f1fe78a538a5c1d3508550942723e506ffe2c8; 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

原文未注明机构

评测协议

LAB-Bench →

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。

BibTeX ↓RIS ↓记录与来源元数据 · JSON ↓阅读覆盖 · JSON 提交更正

原始出版物 · BibTeX

@misc{lab-bench,
  title = {LAB-Bench Measuring Capabilities of Language Models for Biology Research},
  url = {https://arxiv.org/abs/2407.10362},
  year = {2024},
  date = {2024-07-14},
  version = {2026-10-25 source capture},
  note = {2026-10-25 source capture}
}

NUWA 记录 · BibTeX

@misc{lab-bench-nuwa,
  title = {LAB-Bench Measuring Capabilities of Language Models for Biology Research — NUWA research record},
  url = {https://whitzard.tech/nuwa/whitzard-index/work/lab-bench/},
  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--lab-bench.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--lab-bench.json.}
}

证据快照 2026-10-29.1 · 索引更新 · RSS

参考文献

[1] LAB-Bench. 2024-07-14 ; Abstract; §2.1 Dataset description and construction; §3 Discussion and Limitations