BioProBench: A Corpus and Benchmark for Biological Protocol Reasoning in Autonomous Science 文章

ArXiv CS.CL2026-07-28PAPERen作者: Yuyang Liu, Liuzhenghao Lv, Xiancheng Zhang, Jingya Wang Li Yuan, Yonghong Tian

详细信息

来源站点
ArXiv CS.CL
作者
Yuyang Liu, Liuzhenghao Lv, Xiancheng Zhang, Jingya Wang Li Yuan, Yonghong Tian
文章类型
PAPER
语言
en
发布日期
2026-07-28

摘要

arXiv:2505.07889v4 Announce Type: replace Abstract: The realization of autonomous scientific experimentation is currently limited by LLMs' struggle to grasp the strict procedural logic and accuracy required by biological protocols. To address this fundamental challenge, we present \textbf{BioProBench}, a comprehensive resource for procedural reasoning in biology. BioProBench is grounded in \textbf{BioProCorpus}, a foundational collection of 22,413 human-written protocols. From this corpus, we systematically constructed a dataset of 523,784 task instances, offering both a large-scale training resource and a rigorous benchmark with novel metrics. Evaluating 10 mainstream LLMs, we find that while general comprehension is high, performance drops significantly on tasks demanding deep reasoning, quantitative precision, and safety awareness.

相关事件

暂无数据

相关公司查看全部 (3)

A
ARENEGOVERNMENT
A
ANDINONPROFIT

相关人物

暂无数据