Target conducted research on improving RAG results by including bi- and cross-encoders in the process and using completely synthetic training data.
Public source
Publisher name
Public post
Some continued research on trying to improve RAG results, now with bi- and cross- encoders included in the process to see if we can start moving the needle in the right…
Company
Target
To help all families discover the joy of everyday life.
- Industry
- Retail
- Location
- Minneapolis, US
- Company size
- 10,001+ employees
About Target
Target is one of the world’s most recognized brands and one of America’s leading retailers. We make Target our guests’ preferred shopping destination by offering outstanding value, inspiration, innovation and an exceptional guest experience that no other retailer can deliver. Target is committed to responsible corporate citizenship, ethical business practices, environmental stewardship and generous community support. Since 1946, we have given 5 percent of our profits back to our communities. Our goal is to work as one team to fulfill our unique brand promise to our guests, wherever and whenever they choose to shop. For more information, visit corporate.target.com. Beware of Hiring Scams: Target will never ask you to submit personal information via a text message for a position. Target will only ask you to apply for positions through corporate.target.com/careers, or Workday, our applicant tracking system.
See moreLatest activity
Latest activity from Target
48 signals
People
Target employee Diego P. served as a reservist for the United States Air Force and guest advocate for T-2051 Huntington Beach in California.
Presence & Recognition
Target recognized Q2 Operations Manager Award winners at T-3881 FDC, Upper Marlboro, MD for their impact throughout Q2.
People
Target is looking to hire a Sr. Financial Analyst for the Corporate Development team
Discover more
Similar signals
Similar public activity from other companies.
Research & Knowledge
Towards Data Science
Towards Data Science published a research paper comparing cost, latency, and answer quality using a million-token context window and Kimi K3 with a RAG pipeline.
Research & Knowledge
H&M
H&M researchers ran a real experiment involving three AI experiments to detect specific problem-solving abilities on a model's output.
Research & Knowledge
Gap
Gap created a Lama-based hybrid Mamba-2 + sparse MoE + light attention stack pretrained for agents stretched to 1M-token context.
Research & Knowledge
Verizon
Verizon conducted an experiment to find the optimal Top-K value for retrieval in RAG Ablation Lab.
Research & Knowledge
Collibra