Reducing hallucination in structured outputs via Retrieval-Augmented Generation

Orlando Ayala, Patrice Bechard

Abstract
A current 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 hallucination, real-world GenAI systems will likely continue to face challenges in user adoption. In the process of deploying an enterprise application that produces workflows from natural language requirements, we devised a system leveraging Retrieval-Augmented Generation (RAG) to improve the quality of the structured output that represents such workflows. Thanks to our implementation of RAG, our proposed system significantly reduces hallucination and allows the generalization of our LLM to out-of-domain settings. In addition, we show that using a small, well-trained retriever can reduce the size of the accompanying LLM at no loss in performance, thereby making deployments of LLM-based systems less resource-intensive.
Anthology ID:
2024.naacl-industry.19
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 6: Industry Track)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Yi Yang, Aida Davani, Avi Sil, Anoop Kumar
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
228–238
Language:
URL:
https://aclanthology.org/2024.naacl-industry.19
DOI:
Bibkey:
Cite (ACL):
Orlando Ayala and Patrice Bechard. 2024. Reducing hallucination in structured outputs via Retrieval-Augmented Generation. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 6: Industry Track), pages 228–238, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Reducing hallucination in structured outputs via Retrieval-Augmented Generation (Ayala & Bechard, NAACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/jeptaln-2024-ingestion/2024.naacl-industry.19.pdf
PDF Search