데이터 구조와 리소스 기반의 LLM Alignment 최적 전략 분석
RLHF vs DPO vs IPO vs KTO: which alignment method should you use
RLHF vs DPO vs IPO vs KTO: which alignment method should you use
Subjectivation: A protocol to give LLMs a functional, responsible self
Claude AI: Features, Capabilities & Why It Stands Out in 2026
Why I Built an AI That Tries to Destroy Your Legal Argument
Constitutional AI with Open LLMs
Preference Tuning LLMs with Direct Preference Optimization Methods