# SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond

arXiv: https://arxiv.org/abs/2603.01589 · HTML: https://mlsanity.com/paper/2603.01589/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Mar 2026.

## Built on by (most cited first, 2 of 2)

- [An Early Warning of Emerging Biosecurity Risks in Frontier LLMs](https://mlsanity.com/paper/2607.18056/) (2026)
- [SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring](https://mlsanity.com/paper/2607.18665/) (2026)

## Abstract (arXiv)

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.