Se2 ist eine innovative Methode für die sequenzielle Auswahl von Beispielen für das In-Context Learning, die die Leistung von Large Language Models verbessert.
Se2은 순차적 선택 방법을 통해 In-Context Learning을 향상시키는 효과적인 방법을 제안합니다.
Large language models require effective example selection for in-context learning, which Se2 achieves through a sequential-aware method and beam search strategy.
In this paper, the authors introduce Se2, a sequential-aware method that enhances in-context learning by selecting ideal example sequences. Through extensive experiments, Se2 outperforms competitive baselines and demonstrates significant improvements in performance.