Embedding-based In-Context Prompt Training for Enhancing LLMs as Text Encoders

ArXi:2605.01372v1 Announce Type: new Large language models (LLMs) have been widely explored for embedding generation. While recent studies show that in-context learning (ICL) effectively enhances the representational capability of LLMs by prepending a few task-related nstrations, it causes substantial token overhead due to the increased sequence length. In this work, we propose EPIC, a novel embedding-based in-context prompt