본문으로 건너뛰기

Juhyeon's Blog

태그: benchmark-evaluation

3건의 항목

  • 2026년 11월 01일

    Helpful to a Fault - Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents

    • 논문
    • red-teaming
    • agent-safety
    • multilingual-jailbreak
    • benchmark-evaluation
  • 2026년 11월 01일

    Position - There are futures that benchmark-driven AI cannot see

    • metascience
    • benchmark-evaluation
    • exaptation
    • ai-safety
    • research-methodology
    • position-paper
  • 2026년 11월 01일

    The Personality Illusion - Revealing Dissociation Between Self-Reports and Behavior in LLMs

    • LLM
    • personality
    • self-report-vs-behavior
    • BigFive
    • persona-injection
    • RLHF
    • alignment
    • behavioral-validity
    • benchmark-evaluation

키보드 단축키

/ 또는 Ctrl+K검색
?단축키 도움말
Esc모달 닫기
  • GitHub