Summary of Eratta: Extreme Rag For Table to Answers with Large Language Models, by Sohini Roychowdhury et al.
ERATTA: Extreme RAG for Table To Answers with Large Language Models
by Sohini Roychowdhury, Marko Krema, Anvar Mahammad, Brian Moore, Arijit Mukherjee, Punit Prakashchandra
First submitted to arxiv on: 7 May 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed paper presents a unique approach to scalable generative AI solutions by leveraging large language models (LLMs) with retrieval augmented-generation (RAG). The authors aim to address the limitations of existing RAG-LLM approaches, which are often generic or domain-specific, and lack scalability. The paper introduces an LLM-based system that enables data authentication, user-query routing, data-retrieval, and custom prompting for question-answering capabilities from Enterprise-data tables. This framework achieves structured responses in under 10 seconds per query and detects hallucinations in LLM responses using a five-metric scoring module. The proposed system demonstrates >90% confidence scores across hundreds of user queries in sustainability, financial health, and social media domains. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper proposes a new way to use big language models (LLMs) for fast and accurate answers from large data sets. Right now, these LLMs are often used with retrieval augmented-generation (RAG), but this combination has some limitations. The authors want to make RAG-LLM more scalable and generalizable by introducing a unique system that can handle big data tables and provide answers quickly. This system is designed for use in Enterprises and can handle fluctuating data sets. It also includes a special module that detects when the LLM makes something up, which happens very rarely. |
Keywords
» Artificial intelligence » Prompting » Question answering » Rag » Retrieval augmented generation
