作者位次 #4/8ACL 2026Poster· Natural Language Processing
AEA : Adaptive Expert Allocation Improves Sentence Embeddings from Mixture-of-Experts LLM
Shufan Yang · Zifeng Cheng · Zhiwei Jiang · Qingfeng Qi · Yafeng Yin · Cong Wang · Ao Zhou · Qing Gu
摘要
Extracting embeddings directly from Mixture-of-Experts (MoE) models is a promising yet underexplored direction that requires no additional data or fine-tuning. While previous studies have utilized semantic compression prompts or expert routing information to improve sentence embeddings, they typi...