Method
DPO / preference optimization
Preference tuning without RL loop (DPO, CPO, IPO).
6 cases from 6 companies apply DPO / preference optimization. 1 was checked in an online A/B test; 1 report results in production.
Typical tasks: Analyze user behavior, Label data with LLMs, Evaluate models, Recommend from what the user just did. Companies: Pinterest, Spotify, Netflix, Wildberries, Yandex and 1 more. Often combined with: Supervised fine-tuning, LLM-as-a-judge, Knowledge distillation, LoRA fine-tuning, Synthetic data generation (LLM) and 21 more.
| From Activity to Intent: Generating User Journeys with LLMs | social | 2026-10 | |
Doubling Medical Safety: Fine-Tuning Open LLMs for Women's Health Without Human Labels![]() | ![]() | healthtech | 2026-06 |
| Inside the Archive: The Tech Behind Your 2025 Wrapped Highlights | media-streaming | 2026-03 | |
| Post-Training Generative Recommenders with Advantage-Weighted Supervised Finetuning | media-streaming | 2025-10 | |
An LLM Reads Marketplace Reviews for You![]() | ![]() | marketplace | 2024-05 |
On Adapting LLMs to HTML Translation![]() | ![]() | search-engine | 2024-05 |


