Abhishek Sharma

The field of Generative AI has seen rapid advancements, yet the challenge remains in effectively measuring and validating these systems’ outputs. This session provides a comprehensive overview of the evaluation techniques that are pivotal for Generative AI systems, particularly those involving retrieval-augmented generation (RAG). We will dive into the intricacies of retrieval evaluation, discussing key metrics that help assess the relevance and accuracy of information retrieved by AI. Following this, we transition into evaluating generative aspects, exploring how these metrics ensure the generated content meets the desired standards of coherence and relevance.