https://github.com/ZJunBo/DataShield

• DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning

  DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning arXiv:2606.00160v1 Announce Type: new Abstract: Large language models (LLMs) suffer from degraded safety capabilities even when fine-tuned with benign datasets. However, existing methods for ident

All reports →

• Connector · intel_report_ingest1