Refining Input Guardrails: Enhancing LLM-as-a-Judge Efficiency Through Chain-of-Thought Fine-Tuning and Alignment

Documenti analoghi

• STELP: Secure Transpilation and Execution of LLM-Generated Programs
  di: Shinde, Swapnil, et al.
  Pubblicazione: (2026)
• Building Safe GenAI Applications: An End-to-End Overview of Red Teaming for Large Language Models
  di: Purpura, Alberto, et al.
  Pubblicazione: (2025)
• GRAID: Synthetic Data Generation with Geometric Constraints and Multi-Agentic Reflection for Harmful Content Detection
  di: Rad, Melissa Kazemi, et al.
  Pubblicazione: (2025)
• Refine-n-Judge: Curating High-Quality Preference Chains for LLM-Fine-Tuning
  di: Cayir, Derin, et al.
  Pubblicazione: (2025)
• Adaptive Instruction Composition for Automated LLM Red-Teaming
  di: Zymet, Jesse, et al.
  Pubblicazione: (2026)