Information Retrieval and Language Models

5 repos

This cluster encompasses repositories focused on retrieval-augmented generation, dense passage retrieval, reinforcement learning from human feedback, and large language model development. The central repos suggest work on Wikipedia-based retrieval systems, model training pipelines, and release management for ML assets, indicating an active area combining information retrieval with modern LLM techniques. Explorers will find infrastructure, datasets, and methodologies for building systems that combine retrieval with generative language models.