Concept

Fine-Tuning LLMs to Refuse Answering in RAG

A specific method to enhance Retrieval-Augmented Generation (RAG) involves fine-tuning the Large Language Model with human-labeled data. This supervised training teaches the model to recognize when the retrieved context is inadequate and to refuse to provide an answer, thereby improving its reliability.

0

1

Updated 2025-10-06

Contributors are:

Who are from:

Tags

Ch.3 Prompting - Foundations of Large Language Models

Foundations of Large Language Models

Foundations of Large Language Models Course

Computing Sciences