# Satyrn: A Platform for Analytics Augmented Generation

arXiv: https://arxiv.org/abs/2406.12069 · HTML: https://mlsanity.com/paper/2406.12069/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation.
- Builds on 22 of its 55 references that are in the map.
- First posted on arXiv 17 Jun 2024.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 22 of 22)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback](https://mlsanity.com/paper/2302.12813/) (2023)
- [ToolQA: A Dataset for LLM Question Answering with External Tools](https://mlsanity.com/paper/2306.13304/) (2023)
- [Towards a Unified Multi-Dimensional Evaluator for Text Generation](https://mlsanity.com/paper/2210.07197/) (2022)
- [A Categorical Archive of ChatGPT Failures](https://mlsanity.com/paper/2302.03494/) (2023)
- [The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey](https://mlsanity.com/paper/2404.11584/) (2024)
- [Unsupervised Commonsense Question Answering with Self-Talk](https://mlsanity.com/paper/2004.05483/) (2020)
- [Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering](https://mlsanity.com/paper/2306.04136/) (2023)
- [Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering](https://mlsanity.com/paper/1911.03868/) (2019)
- [Plan-then-Generate: Controlled Data-to-Text Generation via Planning](https://mlsanity.com/paper/2108.13740/) (2021)
- [Data-to-text Generation with Entity Modeling](https://mlsanity.com/paper/1906.03221/) (2019)
- [Hindsight: Posterior-guided training of retrievers for improved open-ended generation](https://mlsanity.com/paper/2110.07752/) (2021)
- [Teaching machines to understand data science code by semantic enrichment of dataflow graphs](https://mlsanity.com/paper/1807.05691/) (2018)
- [ReTAG: Reasoning Aware Table to Analytic Text Generation](https://mlsanity.com/paper/2305.11826/) (2023)

## Built on by (most cited first, 2 of 2)

- [RingSQL: Schema-Independent Synthetic Data Generation for Text-to-SQL Reinforcement Learning](https://mlsanity.com/paper/2601.05451/) (2026)
- [Tytan: Interactive Neurosymbolic Construction of Analytic Semantic Schemas from Relational Data](https://mlsanity.com/paper/2608.06331/) (2026)

## Abstract (arXiv)

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.