RAG vs PEFT - Comparing LLM Domain Adaptation Methods

Explore a technical conference presentation from SK TECH SUMMIT 2023 that delves into comparing two key methods for adapting Large Language Models (LLMs) to specific domains: Retrieval-Augmented Generation (RAG) and Parameter-Efficient Fine-Tuning (PEFT). Learn from SK Broadband's practical experience implementing these approaches using internal data sources like customer service manuals and legal documentation. Gain valuable insights into building AWS environments for LLM/sLLM model deployment and developing domain-specific LLM models. The speaker, Hyunseok Kim from SK Broadband, brings expertise from autonomous vehicle research and semiconductor industry experience, currently working as a data scientist focusing on NLP applications for content metadata discovery and viewing prediction tasks.