Preprint
Jul 2026
DataShield: Uncovering Risky Fine-Tuning Data Across LLMs Through Consensus Subspace Alignment
DataShield is a data assessment framework that identifies risky fine-tuning samples and response segments through consensus subspace alignment over joint safety-critical semantic spaces derived from multiple safety-aligned LLMs, allowing both sample-level filtering and fine-grained segment-level masking.
Zefeng Wu, Weiwei Qi, Jielong Chen et al.
· 4 citations