Reducing hallucination in structured outputs via Retrieval-Augmented Generation

Abstract

A common and fundamental limitation of Generative AI (GenAI) is its propensity to hallucinate. While large language models (LLM) have taken the world by storm, without eliminating or at least reducing hallucinations, real-world GenAI systems may face challenges in user adoption. In the process of deploying an enterprise application that produces workflows based on natural language requirements, we devised a system leveraging Retrieval Augmented Generation (RAG) to greatly improve the quality of the structured output that represents such workflows. Thanks to our implementation of RAG, our proposed system significantly reduces hallucinations in the output and improves the generalization of our LLM in out-of-domain settings. In addition, we show that using a small, well-trained retriever encoder can reduce the size of the accompanying LLM, thereby making deployments of LLM-based systems less resource-intensive.

To be presented at NAACL 2024. 11 pages and 4 figures

Cited by in corpus (5)

• Understanding Attitudes and Trust of Generative AI Chatbots for Social Anxiety Support
• A Survey on Knowledge Organization Systems of Research Fields: Resources and Challenges
• Understanding the Fundamental Design Decisions of Retrieval-Augmented Generation Systems
• Hallucinations in LLMs: A Lifecycle-Based Survey of Causes, Detection, Mitigation, and Prevention
• What Characteristics Make ChatGPT Effective for Software Issue Resolution? An Empirical Study of Task, Project, and Conversational Signals in GitHub Issues