Tool
XLM-RoBERTa
8 cases from 7 companies use XLM-RoBERTa in their stack. 2 were checked in an online A/B test; 1 report results in production. Tasks: Rank search results, Retrieve and rank from millions of items, Match entities, Get experiment results faster and 5 more. Methods: Dense retrieval, Cross-encoder reranking, Hybrid search, Threshold selection, Relevance labeling and 30 more. Companies: Pinterest, Atlassian, LY Corporation, SberDevices, CFT and 2 more.
| How Rovo solves search challenges through entity linking | saas-b2b | 2026-01 | |
| LLM-Powered Relevance Assessment for Pinterest Search | social | 2025-12 | |
Developing a multi-label classification model for OpenChat hashtag prediction![]() | ![]() | social | 2025-05 |
| Improving Pinterest Search Relevance Using Large Language Models | social | 2025-04 | |
GigaSearch, or a Search System on GigaChat![]() | ![]() | search-engine | 2024-05 |
| How We Got RAG Running in Production | general | 2024-05 | |
| A System for Recognizing Required Skills in Job Postings: Skill ProfilingSC | SC | general | 2024-05 |
| Learning to Understand Dialogs Based on Real DataCF | CF | fintech | 2023-10 |

