WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia

WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia

This paper describes a really interesting LLM system that runs Retrieval Augmented Generation against Wikipedia to help answer questions, but includes a second step where facts in the answer are fact-checked against Wikipedia again before returning an answer to the user. They claim "97.3% factual accuracy of its claims in simulated conversation" on a GPT-4 backed version, and also see good results when backed by LLaMA …

ai chatbots facts few-shot generativeai hallucination language language model large language large language model llm llms paper promptengineering questions retrieval retrieval augmented generation wikipedia