Beyond Creed: A Non-Identity Safety Condition A Strong Empirical Alternative to Identity Framing in Low-Data LoRA Fine-Tuning

Documenti analoghi

• DR-LoRA: Dynamic Rank LoRA for Fine-Tuning Mixture-of-Experts Models
  di: Deng, Guanzhi, et al.
  Pubblicazione: (2026)
• KD-LoRA: A Hybrid Approach to Efficient Fine-Tuning with LoRA and Knowledge Distillation
  di: Azimi, Rambod, et al.
  Pubblicazione: (2024)
• HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning
  di: Tian, Chunlin, et al.
  Pubblicazione: (2024)
• LoRA-PAR: A Flexible Dual-System LoRA Partitioning Approach to Efficient LLM Fine-Tuning
  di: Huang, Yining, et al.
  Pubblicazione: (2025)
• $D^2LoRA$: Data-Driven LoRA Initialization for Low Resource Tasks
  di: SeraJ, Javad, et al.
  Pubblicazione: (2025)