SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2411.00786 · 2024

Interpret and Control Dense Retrieval with Sparse Latent Features

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Dense embeddings deliver strong retrieval performance but often lack interpretability and controllability. This paper introduces a novel approach using sparse autoencoders (SAE) to interpret and control dense embeddings via the learned latent sparse features. Our key contribution is the development of a retrieval-oriented contrastive loss, which ensures the sparse latent features remain effective for retrieval tasks and thus meaningful to interpret. Experimental results demonstrate that both the learned latent sparse features and their reconstructed embeddings retain nearly the same retrieval accuracy as the original dense vectors, affirming their faithfulness. Our further examination of the sparse latent space reveals interesting features underlying the dense embeddings and we can control the retrieval behaviors via manipulating the latent sparse features, for example, prioritizing documents from specific perspectives in the retrieval results.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2411.00786")
get_code_for_paper("2411.00786")
have("2411.00786")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2411.00786.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2411.00786.svg)](https://syntology.ai/paper/2411.00786)

Connect an agent — have() is free.