AI Paper Atlas

Research map / Large language models / Instruction and fine-tuning

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

Xiangyang Zhu, Yuan Tian, Qi Jia, Kaiwei Zhang, Zicheng Zhang, Chunyi Li, Zijian Chen, Lu Sun, Kaiyuan Ji, Renrui Zhang, Wei Sun, Guangtao Zhai

ICML 2026 · Large language models › Instruction and fine-tuning · approach: Safety alignment after fine-tuning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add LoRA fine-tuning on SafeSciTrainQwen3-8B · SafeSciBench safety knowledge (overall)accuracy: 0.59 -> 0.70Improved
add LoRA fine-tuning on SafeSciTrainQwen3-14B · SafeSciBench safety knowledge (overall)accuracy: 0.60 -> 0.75Improved
add LoRA fine-tuning on SafeSciTrainLlama-3.1-8B-Instruct · SafeSciBench safety knowledge (overall)accuracy: 0.57 -> 0.66Improved
add LoRA fine-tuning on SafeSciTrainQwen3-8B · SafeSciBench safety risk (overall)safety rate: 0.31 -> 0.64Improved
add LoRA fine-tuning on SafeSciTrainQwen3-14B · SafeSciBench safety risk (overall)safety rate: 0.26 -> 0.60Improved
add LoRA fine-tuning on SafeSciTrainLlama-3.1-8B-Instruct · SafeSciBench safety risk (overall)safety rate: 0.41 -> 0.58Improved
add LoRA fine-tuning on SafeSciTrainQwen3-8B · SafeSciBench safety knowledge (Biology)accuracy: 0.56 -> 0.42Hurt
add LoRA fine-tuning on SafeSciTrainLlama-3.1-8B-Instruct · SafeSciBench safety knowledge (Biology)accuracy: 0.75 -> 0.42Hurt
add LoRA fine-tuning on SafeSciTrainQwen3-8B · SafeSciBench safety risk (Psychology)safety rate: 0.14 -> 0.08Hurt
add LoRA fine-tuning on SafeSciTrainQwen3-8B · SafeSciBench safety risk (Engineering)safety rate: 0.16 -> 0.19No clear effect
increase model size Qwen3-8B to 32BQwen3 · SafeSciBench safety knowledge (overall)accuracy: 0.59 -> 0.62Improved
increase model size Qwen3-8B to 32BQwen3 · SafeSciBench safety risk (overall)safety rate: 0.31 -> 0.36No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy