Saved in:
Bibliographic Details
Main Authors: Zhu, Xiangyang, Tian, Yuan, Jia, Qi, Zhang, Kaiwei, Zhang, Zicheng, Li, Chunyi, Ji, Kaiyuan, Liu, Dongrui, Chen, Zijian, Sun, Lu, Zhang, Renrui, Teng, Yan, Shao, Jing, Sun, Wei, Hu, Xia, Qiao, Yu, Zhai, Guangtao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.01589
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913000339800064
author Zhu, Xiangyang
Tian, Yuan
Jia, Qi
Zhang, Kaiwei
Zhang, Zicheng
Li, Chunyi
Ji, Kaiyuan
Liu, Dongrui
Chen, Zijian
Sun, Lu
Zhang, Renrui
Teng, Yan
Shao, Jing
Sun, Wei
Hu, Xia
Qiao, Yu
Zhai, Guangtao
author_facet Zhu, Xiangyang
Tian, Yuan
Jia, Qi
Zhang, Kaiwei
Zhang, Zicheng
Li, Chunyi
Ji, Kaiyuan
Liu, Dongrui
Chen, Zijian
Sun, Lu
Zhang, Renrui
Teng, Yan
Shao, Jing
Sun, Wei
Hu, Xia
Qiao, Yu
Zhai, Guangtao
contents The success of large language models (LLMs) in scientific domains has heightened safety concerns, prompting numerous benchmarks to evaluate their scientific safety. Existing benchmarks often suffer from limited risk coverage and a reliance on subjective evaluation. To address these problems, we introduce SafeSci, a comprehensive framework for safety evaluation and enhancement in scientific contexts. SafeSci comprises SafeSciBench, a multi-disciplinary benchmark with 0.25M samples, and SafeSciTrain, a large-scale dataset containing 1.5M samples for safety enhancement. SafeSciBench distinguishes between safety knowledge and risk to cover extensive scopes and employs objective metrics such as deterministically answerable questions to mitigate evaluation bias. We evaluate 24 advanced LLMs, revealing critical vulnerabilities in current models. We also observe that LLMs exhibit varying degrees of excessive refusal behaviors on safety-related issues. For safety enhancement, we demonstrate that fine-tuning on SafeSciTrain significantly enhances the safety alignment of models. Finally, we argue that knowledge is a double-edged sword, and determining the safety of a scientific question should depend on specific context, rather than universally categorizing it as safe or unsafe. Our work provides both a diagnostic tool and a practical resource for building safer scientific AI systems.
format Preprint
id arxiv_https___arxiv_org_abs_2603_01589
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond
Zhu, Xiangyang
Tian, Yuan
Jia, Qi
Zhang, Kaiwei
Zhang, Zicheng
Li, Chunyi
Ji, Kaiyuan
Liu, Dongrui
Chen, Zijian
Sun, Lu
Zhang, Renrui
Teng, Yan
Shao, Jing
Sun, Wei
Hu, Xia
Qiao, Yu
Zhai, Guangtao
Machine Learning
Artificial Intelligence
The success of large language models (LLMs) in scientific domains has heightened safety concerns, prompting numerous benchmarks to evaluate their scientific safety. Existing benchmarks often suffer from limited risk coverage and a reliance on subjective evaluation. To address these problems, we introduce SafeSci, a comprehensive framework for safety evaluation and enhancement in scientific contexts. SafeSci comprises SafeSciBench, a multi-disciplinary benchmark with 0.25M samples, and SafeSciTrain, a large-scale dataset containing 1.5M samples for safety enhancement. SafeSciBench distinguishes between safety knowledge and risk to cover extensive scopes and employs objective metrics such as deterministically answerable questions to mitigate evaluation bias. We evaluate 24 advanced LLMs, revealing critical vulnerabilities in current models. We also observe that LLMs exhibit varying degrees of excessive refusal behaviors on safety-related issues. For safety enhancement, we demonstrate that fine-tuning on SafeSciTrain significantly enhances the safety alignment of models. Finally, we argue that knowledge is a double-edged sword, and determining the safety of a scientific question should depend on specific context, rather than universally categorizing it as safe or unsafe. Our work provides both a diagnostic tool and a practical resource for building safer scientific AI systems.
title SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2603.01589