SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Tasks
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929631980945408 |
|---|---|
| author | Li, Tianhao Lu, Jingyu Chu, Chuangxin Zeng, Tianyu Zheng, Yujia Li, Mei Huang, Haotian Wu, Bin Liu, Zuoxian Ma, Kai Yuan, Xuejing Wang, Xingkai Ding, Keyan Chen, Huajun Zhang, Qiang |
| author_facet | Li, Tianhao Lu, Jingyu Chu, Chuangxin Zeng, Tianyu Zheng, Yujia Li, Mei Huang, Haotian Wu, Bin Liu, Zuoxian Ma, Kai Yuan, Xuejing Wang, Xingkai Ding, Keyan Chen, Huajun Zhang, Qiang |
| contents | Large language models (LLMs) have a transformative impact on a variety of scientific tasks across disciplines including biology, chemistry, medicine, and physics. However, ensuring the safety alignment of these models in scientific research remains an underexplored area, with existing benchmarks primarily focusing on textual content and overlooking key scientific representations such as molecular, protein, and genomic languages. Moreover, the safety mechanisms of LLMs in scientific tasks are insufficiently studied. To address these limitations, we introduce SciSafeEval, a comprehensive benchmark designed to evaluate the safety alignment of LLMs across a range of scientific tasks. SciSafeEval spans multiple scientific languages-including textual, molecular, protein, and genomic-and covers a wide range of scientific domains. We evaluate LLMs in zero-shot, few-shot and chain-of-thought settings, and introduce a "jailbreak" enhancement feature that challenges LLMs equipped with safety guardrails, rigorously testing their defenses against malicious intention. Our benchmark surpasses existing safety datasets in both scale and scope, providing a robust platform for assessing the safety and performance of LLMs in scientific contexts. This work aims to facilitate the responsible development and deployment of LLMs, promoting alignment with safety and ethical standards in scientific research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_03769 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Tasks Li, Tianhao Lu, Jingyu Chu, Chuangxin Zeng, Tianyu Zheng, Yujia Li, Mei Huang, Haotian Wu, Bin Liu, Zuoxian Ma, Kai Yuan, Xuejing Wang, Xingkai Ding, Keyan Chen, Huajun Zhang, Qiang Computation and Language Artificial Intelligence Cryptography and Security Large language models (LLMs) have a transformative impact on a variety of scientific tasks across disciplines including biology, chemistry, medicine, and physics. However, ensuring the safety alignment of these models in scientific research remains an underexplored area, with existing benchmarks primarily focusing on textual content and overlooking key scientific representations such as molecular, protein, and genomic languages. Moreover, the safety mechanisms of LLMs in scientific tasks are insufficiently studied. To address these limitations, we introduce SciSafeEval, a comprehensive benchmark designed to evaluate the safety alignment of LLMs across a range of scientific tasks. SciSafeEval spans multiple scientific languages-including textual, molecular, protein, and genomic-and covers a wide range of scientific domains. We evaluate LLMs in zero-shot, few-shot and chain-of-thought settings, and introduce a "jailbreak" enhancement feature that challenges LLMs equipped with safety guardrails, rigorously testing their defenses against malicious intention. Our benchmark surpasses existing safety datasets in both scale and scope, providing a robust platform for assessing the safety and performance of LLMs in scientific contexts. This work aims to facilitate the responsible development and deployment of LLMs, promoting alignment with safety and ethical standards in scientific research. |
| title | SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Tasks |
| topic | Computation and Language Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2410.03769 |