作者位次 #2/6ACL 2026Findings· Findings of ACL
S em PA : Improving Sentence Embeddings of Large Language Models through Semantic Preference Alignment
Ziyang Chen · Zhenxuan Huang · Yile Wang · Weiqin Wang · Lu Yin · Hui Huang
摘要
Traditional sentence embedding methods employ token-level contrastive learning on non-generative pre-trained models. Recently, there have emerged embedding methods based on generative large language models (LLMs). These methods either rely on fixed prompt templates or involve modifications to the...