Patching LLM Like Software: A Lightweight Method for Improving Safety Policy in Large Language Models

Documenti analoghi

• PEEL the Layers and Find Yourself: Revisiting Inference-time Data Leakage for Residual Neural Networks
  di: Arif, Huzaifa, et al.
  Pubblicazione: (2025)
• Forecasting Fails: Unveiling Evasion Attacks in Weather Prediction Models
  di: Arif, Huzaifa, et al.
  Pubblicazione: (2025)
• Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models
  di: Chen, Pin-Yu, et al.
  Pubblicazione: (2025)
• vLLM Hook v0: A Plug-in for Programming Model Internals on vLLM
  di: Ko, Ching-Yun, et al.
  Pubblicazione: (2026)
• STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Models
  di: Basavatia, Shreyas, et al.
  Pubblicazione: (2024)