Authors: Luke Merrick, Danmei Xu, Gaurav Nuti, Daniel Campos

Published on: May 08, 2024

Impact Score: 7.6

Arxiv code: Arxiv:2405.05374

Summary

• What is new: The introduction of the arctic-embed text embedding models with state-of-the-art retrieval accuracy.
• Why this is important: Lack of open-sourced models that achieve high retrieval accuracy.
• What the research proposes: Creation of arctic-embed text embedding models open-sourced under an Apache-2 license.
• Results: Arctic-embed-l model outperformed existing closed source models like Cohere’s embed-v3 and Open AI’s text-embed-3-large.

Technical Details

Technological frameworks used: Apache-2 license

Models used: arctic-embed text embedding models

Data used: MTEB Retrieval leaderboard

Potential Impact

Text embedding and retrieval market, affecting companies like Cohere and OpenAI.

Want to implement this idea in a business?

We have generated a startup concept here: TextInsightAI.