SAFENLIDB: A Privacy-Preserving Safety Alignment Framework for LLM-based Natural Language Database Interfaces

Documenti analoghi

• Filling Memory Gaps: Enhancing Continual Semantic Parsing via SQL Syntax Variance-Guided LLMs without Real Data Replay
  di: Liu, Ruiheng, et al.
  Pubblicazione: (2024)
• Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL
  di: Hong, Zijin, et al.
  Pubblicazione: (2024)
• Evil Geniuses: Delving into the Safety of LLM-based Agents
  di: Tian, Yu, et al.
  Pubblicazione: (2023)
• SaRO: Enhancing LLM Safety through Reasoning-based Alignment
  di: Mou, Yutao, et al.
  Pubblicazione: (2025)
• Decoupling Safety into Orthogonal Subspace: Cost-Efficient and Performance-Preserving Alignment for Large Language Models
  di: Mou, Yutao, et al.
  Pubblicazione: (2025)