본문으로 건너뛰기
Juhyeon's Blog
Search
검색
다크 모드
라이트 모드
탐색기
태그: benchmark/evaluation
2건의 항목
2026년 11월 01일
CAR-bench - Evaluating the Consistency and Limit-Awareness of LLM Agents under Real-World Uncertainty
field/LLM-agents
benchmark/evaluation
insight/experimental
topic/reliability
topic/uncertainty
topic/tool-use
confidence/medium
2026년 11월 01일
Spotting Out-of-Character Behavior - Atomic-Level Evaluation of Persona Fidelity in Open-Ended Generation
field/NLP
field/LLM-evaluation
insight/methodological
topic/persona-fidelity
topic/role-play
topic/out-of-character
benchmark/evaluation
confidence/high