Method
RLHF
Aligning models with human preference feedback via PPO-style reinforcement learning.
6 cases from 2 companies apply RLHF. 2 were checked in an online A/B test.
Typical tasks: Label data with LLMs, Evaluate models, Build an assistant over internal docs. Companies: Rabota.ru, Wildberries. Often combined with: Supervised fine-tuning, Reward model, PPO, LoRA fine-tuning, Abstractive summarization and 20 more.
| Advanced Use of GigaChat at Rabota.ru: Synthetic Data and Search | classifieds | 2024-05 | |
An LLM Reads Marketplace Reviews for You![]() | ![]() | marketplace | 2024-05 |
| Siren Song in the Sea of AI: Hallucinations of Language Models | — | general | 2023-10 |
| A Job Posting Summary Generation Service Based on an LM Fine-Tuned with RLHF | classifieds | 2023-05 | |
| Creating a Semi-Synthetic Dataset to Fine-Tune a Job Posting Summarization Model with RLHF | classifieds | 2023-05 | |
| LLaMA and a Zillion Ways to Fine-Tune It | — | general | 2023-05 |
