Method

Supervised fine-tuning

Full or domain fine-tuning of models on labeled or instruction data (SFT).

54 cases from 32 companies apply Supervised fine-tuning. 10 were checked in an online A/B test; 20 report results in production.

Typical tasks: Evaluate models, Build an assistant over internal docs, Label data with LLMs, Rank search results and 12 more. Companies: Yandex, Netflix, Yelp, DoorDash, Pinterest, Spotify and 26 more. Often combined with: RAG, LLM-as-a-judge, Knowledge distillation, Synthetic data generation (LLM), Reward model and 123 more.

From Activity to Intent: Generating User Journeys with LLMssocial2026-10
Advancing Generative Recommendation Inference: our collaboration with NVIDIA on TensorRT LLMmedia-streaming2026-10
GenRec: Towards LLM-Native Recommendation at Netflixmedia-streaming2026-07
Thinking Fast & Slow: How Databricks Built High-Speed and Deep Research Agentsgeneral2026-06
Doubling Medical Safety: Fine-Tuning Open LLMs for Women's Health Without Human Labelshealthtech2026-06
How We Do RL for Our LLM at Avitoclassifieds2026-05
The Search of the Futuregeneral2026-05
How to Speed Up Multimodal Labeling Fourfold Without Losing Quality: Training a Compact VLM on Complex Data and Domain Projectsgeneral2026-05
How to Safely Roll Out New Versions of Product AI Agents Using an Auto-Metrics Systeme-commerce2026-05
Building Biz Ask Anything: From Prototype to Productmarketplace2026-03
Inside the Archive: The Tech Behind Your 2025 Wrapped Highlightsmedia-streaming2026-03
Our Early Journey to Transform Instacart’s Discovery Recommendations with LLMse-commerce2026-02
How Etsy Uses LLMs to Improve Search Relevancemarketplace2026-01
LLM-Powered Relevance Assessment for Pinterest Searchsocial2025-12
Integrating Netflix’s Foundation Model into Personalization applicationsmedia-streaming2025-11
How We Brewed RAGU: A System for Quickly Building a Knowledge Graph from Raw Textsgeneral2025-11
Comment ranker - An ML-based classifier to improve LLM code review quality using Atlassian's proprietary datasaas-b2b2025-08
Product Applications of Yandex VLMsearch-engine2025-05
How Large Language Models Help Users Formulate Queries in Yandex Mapssearch-engine2025-05
YandexGPT as a RAG assistant for tech support: solving problems fastergeneral2025-05
How we use LLMs with RAG in LemanaTECH's ecosystem of IT support ML modelsretail2025-05
Building RAG-Like Systems for Few-Shot Intent Classification in Narrow Domainsbanking2025-05
How DoorDash leverages LLMs to evaluate search result pagesfood-delivery2025-04
RoBERTa Model for Merchant Categorization at Squarefintech2025-03
Search Query Understanding with LLMs: From Ideation to Productionmarketplace2025-02
Unleashing the power of large language models at DoorDash for a seamless shopping adventurefood-delivery2024-10
Advanced Use of GigaChat at Rabota.ru: Synthetic Data and Searchclassifieds2024-05
LLMs at Avitoclassifieds2024-05
LLM in Education: How We Created the Code Guardianedtech2024-05
A Personal Mentor Powered by GPTedtech2024-05
Neural Filter with YaGPT: Helping Users Sort Out Their Mailboxgeneral2024-05
An LLM Reads Marketplace Reviews for Youmarketplace2024-05
RAG as a Flexible Method for Creating Language Assistantsgeneral2024-05
Optimizing Marketplace Operations with Language Modelsmarketplace2024-05
An LLM for a Tax Agentgeneral2024-05
Foundation Models: Is There Life in Time Series?general2024-05
How We Got RAG Running in Productiongeneral2024-05
LLM Practice Without Christofarigeneral2024-05
On Adapting LLMs to HTML Translationsearch-engine2024-05
Product ML: Expectations vs. Reality. How to Describe the Organization in Briefgeneral2024-05
Building DoorDash's product knowledge graph with large language modelsfood-delivery2024-04
Yelp’s AI pipeline for inappropriate language detection in reviewsmarketplace2024-03
Building In-Video Searchmedia-streaming2023-11
Siren Song in the Sea of AI: Hallucinations of Language Models—general2023-10
Let AI Entertain You: Increasing User Engagement with Generative AI and Rejection Samplingsocial2023-10
History of the Unified Classifier Developmentbanking2023-05
NLP at Alfa-Bank, Part 7: Analyzing Customer Feedbackbanking2023-05
Creating a Semi-Synthetic Dataset to Fine-Tune a Job Posting Summarization Model with RLHFclassifieds2023-05
LLaMA and a Zillion Ways to Fine-Tune It—general2023-05
Building Airbnb Categories with ML & Human in the Looptravel2023-03