Building and Curating Datasets for RLHF and LLM Fine-tuning

Explore effective strategies for constructing and managing datasets tailored for reinforcement learning from human feedback (RLHF) and large language model (LLM) fine-tuning in this 59-minute workshop. Learn to leverage Argilla, an open-source data platform that integrates human and machine feedback, to enhance your data curation and annotation techniques. Gain valuable insights into improving the performance and adaptability of RLHF and LLM models through Argilla's robust data management capabilities. Led by Daniel Vila Suero, CEO and co-founder of Argilla, this session draws from his extensive experience in linked data, language technologies, and artificial intelligence research.

Building and Curating Datasets for RLHF and LLM Fine-tuning // Daniel Vila Suero // LLMs in Prod Con