Data & AITools-in-Action25min
Fine-Tuning vs. RAG: Two Paths to Smarter Language Models
The need to customize Large Language Models (LLMs) for particular tasks and domains is rapidly increasing as these models become essential to contemporary AI systems. This is made possible by two main methods, each with its own advantages: Fine-Tuning and Retrieval-Augmented Generation (RAG). This talk offers a clear, practical comparison of both methods. We’ll explore real-world use cases, trade-offs, and hands-on demos showing how to build and evaluate simple fine-tuned and RAG-based models. Attendees will leave with a solid understanding of when to fine-tune, when to retrieve, and how to combine both effectively.
Hajar GharbiRS2i
talkDetail.whenAndWhere
Thursday, November 13, 17:30-17:55
Mimosa 2
The need to customize Large Language Models (LLMs) for particular tasks and domains is rapidly increasing as these models become essential to contemporary AI systems. This is made possible by two main methods, each with its own advantages: Fine-Tuning and Retrieval-Augmented Generation (RAG). This talk offers a clear, practical comparison of both methods. We’ll explore real-world use cases, trade-offs, and hands-on demos showing how to build and evaluate simple fine-tuned and RAG-based models. Attendees will leave with a solid understanding of when to fine-tune, when to retrieve, and how to combine both effectively.
Hajar Gharbi
Hajar GHARBI is a data engineer based in Paris. Her passion for data is reflected in her expertise in data pipelines and Big Data. She is currently also PHD student in the field of generative artificial intelligence (GenAI). Deeply committed to community development, Hajar is involved in collaborative projects and participates in tech events, sharing her expertise through workshops and specialized talks.
comments.speakerNotEnabledComments