핵심 개념
LLMs tend to cluster semantically related words more tightly than classical models, showing higher accuracy on the Bigger Analogy Test Set.
통계
LLM 기반의 임베딩은 전통적인 모델보다 의미론적으로 관련된 단어를 더 밀접하게 클러스터링합니다.
LLM은 Bigger Analogy Test Set에서 더 높은 정확도를 보입니다.
인용구
"Our results show that LLMs tend to cluster semantically related words more tightly than classical models."
"PaLM and ADA, two LLM-based models, tend to agree with each other and yield the highest performance on word analogy tasks."