From Tokens to Concepts: Leveraging SAE for SPLADE 事件

From Tokens to Concepts: Leveraging SAE for SPLADE arXiv:2604.21511v2 Announce Type: replace-cross Abstract: Learned Sparse IR models, such as SPLADE, offer an excellent efficiency-effectiveness tradeoff. However, they rely on the underlying backbone vocabulary, which might hinder performance (polysemicity and synonymy) and pose a challenge for multi-lingual and multi-modal usages. To solve this limitation, we propose to replace the backbone vocabulary with a latent space of semantic concepts l