Quick Start Guide to Large Language Models: Strategies and Best Practices for ChatGPT, Embeddings, Fine-Tuning, and Multimodal AI, 2nd Edition

A

LLM FAQs

The FAQs in this section are a compilation of common queries that arise while working with LLMs. The answers provided here are grounded in the combined wisdom of numerous researchers and practitioners in the field. They can act as a starting point when you face uncertainties or roadblocks in your journey.

The LLM already knows about the domain I’m working in. Why should I add any few-shot examples or grounded content as in RAG?

Yes, your LLM is equipped with pre-trained domain knowledge, but that’s not the whole picture. Grounding—that is, letting an LLM read context from a ground truth in the prompt—or providing a few examples of the task in the prompt boosts the effectiveness of the prompt in almost every situation. It helps in ...