Jinbiao Zhu
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Crypto×2AI×2NLP×2
Frequent co-authors
Research Timeline
2026
DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning
DataShield proposes an efficient method to identify safety-degrading samples within benign datasets, quantifying each sample's contribution to an LLM's compliance behavior.
DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning
DataShield proposes an efficient method to identify safety-degrading samples within benign datasets, preventing the degradation of LLM safety capabilities during fine-tuning.
Highlighted terms show continued research focus across papers
Papers
cs.CRcs.AIcs.CLRecentMay 29, 2026
DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning
Junbo Zhang, Qianli Zhou, Xinyang Deng, Wen Jiang +2 more
DataShield proposes an efficient method to identify safety-degrading samples within benign datasets, quantifying each sample's contribution to an LLM's compliance behavior.
View →
cs.CRcs.AIcs.CLRecentMay 29, 2026