Method

Embedding fine-tuning

Fine-tuning embedding models on domain triplets or synthetic queries.

26 cases from 21 companies apply Embedding fine-tuning. 7 were checked in an online A/B test; 4 report results in production.

Typical tasks: Rank search results, Retrieve and rank from millions of items, Learn user and item embeddings, Build an assistant over internal docs and 5 more. Companies: LinkedIn, Mercari, Wildberries, Atlassian, Criteo, OLX and 15 more. Often combined with: Dense retrieval, Contrastive learning, RAG, LoRA fine-tuning, Two-tower model and 59 more.

Rebuilding LinkedIn's Follows Recommendations with LLM-Based Semantic Retrieval and Rankingsocial2026-08
Semantic Search for AI Agents at Scale: Retrieval and Ranking for LinkedIn’s Hiring Assistantsocial2026-06
Advancing semantic search for millions of Rovo userssaas-b2b2026-03
Leveraging Commerce Data for Outcome-Based Relevancy in Agentic Recommendation Systemsadtech2026-02
Importance of offline evaluation to guide model choiceclassifieds2025-10
Building the next generation of job search at LinkedInmarketplace2025-05
How we use LLMs with RAG in LemanaTECH's ecosystem of IT support ML modelsretail2025-05
Make Retrieval Smarter: How We Built Smart Search over a Document Basegeneral2025-05
RuModernBERT and USERv2: The Evolution of Russian-Language Encodersgeneral2025-05
A Case Study in Recognizing and Structuring Data from Medical Formshealthtech2025-05
JUDE: LLM-based representation learning for LinkedIn job recommendationsmarketplace2025-05
Fine-tuned SigLIP Image Embeddings for Similar Looks Recommendation in a Japanese C2C Marketplacemarketplace2024-11
Improving Retrieval on Ramp with Transaction Embeddingsfintech2024-08
Efficient visual representation learning and evaluationmarketplace2024-06
GigaSearch, or a Search System on GigaChatsearch-engine2024-05
Shazam for Full Names: Finding a Match When a Name Can Be Written 20 Different Waysfintech2024-05
RAG as a Flexible Method for Creating Language Assistantsgeneral2024-05
Optimizing Marketplace Operations with Language Modelsmarketplace2024-05
How We Got RAG Running in Productiongeneral2024-05
Building a Playlist You Will Likemedia-streaming2024-05
RetrievalRecsys: An Architecture Modification to Account for Text in Personal Recommender Systemsmarketplace2024-05
Semantic Search at Zendesksaas-b2b2024-03
Fine-Tuned CLIP: Better Listing Experience and 80% More Budget-Friendlymarketplace2023-12
From Pre-trained to Fine-tuned: Nextdoor’s Path to Effective Embedding Applicationssocial2023-09
Yelp Content As Embeddingsmarketplace2023-04
How Instacart Uses Embeddings to Improve Search Relevancee-commerce2022-09