A safety realignment framework via subspace-oriented model fusion for large language models

Ähnliche Einträge

• Unified attacks to large language model watermarks: spoofing and scrubbing in unauthorized knowledge distillation
  von: Yi, Xin, et al.
  Veröffentlicht: (2025)
• NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning
  von: Yi, Xin, et al.
  Veröffentlicht: (2024)
• Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks
  von: Yi, Xin, et al.
  Veröffentlicht: (2025)
• Hierarchical Divide-and-Conquer for Fine-Grained Alignment in LLM-Based Medical Evaluation
  von: Zheng, Shunfan, et al.
  Veröffentlicht: (2025)
• Fine-Grained Detoxification via Instance-Level Prefixes for Large Language Models
  von: Yi, Xin, et al.
  Veröffentlicht: (2024)