Satyrn: A Platform for Analytics Augmented Generation

Marko Sterbentz, Cameron Barrie, Shubham Shahi, Abhratanu Dutta, Donna Hooshmand, Harper Pack, Kristian Hammond


Abstract
Large language models (LLMs) are capable of producing documents, and retrieval augmented generation (RAG) has shown itself to be a powerful method for improving accuracy without sacrificing fluency. However, not all information can be retrieved from text. We propose an approach that uses the analysis of structured data to generate fact sets that are used to guide generation in much the same way that retrieved documents are used in RAG. This analytics augmented generation (AAG) approach supports the ability to utilize standard analytic techniques to generate facts that are then converted to text and passed to an LLM. We present a neurosymbolic platform, Satyrn, that leverages AAG to produce accurate, fluent, and coherent reports grounded in large scale databases. In our experiments, we find that Satyrn generates reports in which over 86% of claims are accurate while maintaining high levels of fluency and coherence, even when using smaller language models such as Mistral-7B, as compared to GPT-4 Code Interpreter in which just 57% of claims are accurate.
Anthology ID:
2024.emnlp-main.365
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6360–6385
Language:
URL:
https://aclanthology.org/2024.emnlp-main.365
DOI:
Bibkey:
Cite (ACL):
Marko Sterbentz, Cameron Barrie, Shubham Shahi, Abhratanu Dutta, Donna Hooshmand, Harper Pack, and Kristian Hammond. 2024. Satyrn: A Platform for Analytics Augmented Generation. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 6360–6385, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Satyrn: A Platform for Analytics Augmented Generation (Sterbentz et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.365.pdf
Software:
 2024.emnlp-main.365.software.zip