# Reducing Representational Interference in Retrieval Embeddings with Trainable Prefix Tokens > Source: > Published: 2026-11-06 12:30:22+00:00 Embedding models compress variable-length text into fixed-size vector representations, but this compression can entangle semantic content with residual token-level information, such as artifacts arising from attention sink behavior. We propose a simple method that prepends trainable [DUMP] tokens to