100% Elimination of Hallucinations on RAGTruth for GPT-4 and GPT-3.5 Turbo

TL;DR

This paper introduces Acurai, a novel method that reformats queries and context data to eliminate hallucinations in large language models like GPT-4 and GPT-3.5 Turbo, achieving 100% factual accuracy in responses.

Contribution

Acurai is a systematic approach that leverages understanding of LLM internal representations to ensure alignment and eliminate hallucinations in RAG systems.

Findings

Achieves 100% hallucination-free responses on RAGTruth corpus.

Outperforms current methods with over 80% accuracy in factual generation.

Validates effectiveness on GPT-4 and GPT-3.5 Turbo.

Abstract

The issue of hallucinations in large language models (LLMs) remains a critical barrier to the adoption of AI in enterprise and other high-stakes applications. Despite advancements in retrieval-augmented generation (RAG) systems, current state-of-the-art methods fail to achieve more than 80% accuracy in generating faithful and factually correct outputs, even when provided with relevant and accurate context. In this work, we introduce Acurai, a novel systematic approach that achieves 100% hallucination-free responses in LLMs by reformatting queries and context data prior to input. Leveraging a deep understanding of LLM internal representations, the importance of noun-phrase dominance, and the role of discrete functional units (DFUs), Acurai ensures alignment between input context and generated output. We validate this method using the RAGTruth corpus, demonstrating its ability to eliminate 100% hallucinations for both GPT-4 and GPT-3.5 Turbo. Acurai sets a new standard for achieving consistent, accurate, and faithful AI responses, marking a significant step forward in the development of trustworthy AI systems.