Raw static token vectors are a poor fit for MaxSim

Markewich advises against scoring raw static token vectors with MaxSim: it performed worse than standard pooling in the team’s exploration, changes the training target, and assumes contextualized vectors that static embeddings do not provide.

Logan Markewich·已发布 2026年8月26日

观点背后的信息

译文仅辅助阅读；核查观点请以原始摘录为准。

Exploring Static Embedding Retrieval

原始摘录

Don't score raw static token vectors with MaxSim. It's worse than the standard pooling, the scoring method is technically changing the training target. MaxSim assumes contextualized vectors and static embeddings are not contextual.

此片段未附更多上下文，请阅读原始访谈。

打开原始内容 · 段落 45 查看这场访谈

打开该集并跳转至—。

位置来自原始文本；请结合原文语境核对措辞与归属。