SafeScientist: Enhancing AI Scientist Safety for Risk-Aware Scientific Discovery

SafeScientist: Повышение безопасности AI-учёного для риск-ориентированных научных открытий
Yue Su, Jiaxuan You, Kunlun Zhu, Jiaxun Zhang, Ziheng Qi, Nuoxing Shang, Zijia Liu, Peixuan Han, Haofei Yu
2025-01-01

AI scientist safetyEMNLP 2025SafeScientistrisk-aware scientific discoverysafety enhancement for AI-driven discovery
Kunlun Zhu, Jiaxun Zhang, Ziheng Qi, Nuoxing Shang, Zijia Liu, Peixuan Han, Yue Su, Haofei Yu, Jiaxuan You. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
1
Aims to mitigate safety risks associated with automated scientific research conducted by AI systems.
2
Focuses on improving AI-driven scientific discovery by incorporating risk awareness into the discovery process.
3
Introduces SafeScientist, a system to enhance AI scientist safety for risk-aware scientific discovery.
4
Presents methods or framework that integrate safety considerations into AI scientist workflows (SafeScientist).

AI scientist system (SafeScientist) used for automated scientific discovery

Enhancing safety and risk-awareness of the AI scientist during scientific discovery, including risk-aware decision-making and mitigation mechanisms

Publication Details
Publication Date
2025-01-01
Journal
Publisher
ISSN
Cited by
0
Access Type
Author Information
Authors
Yue Su
Jiaxuan You
Kunlun Zhu
Jiaxun Zhang
Ziheng Qi
Nuoxing Shang
Zijia Liu
Peixuan Han
Haofei Yu
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat
Make a presentation
100%