Summary of Facts About Building Retrieval Augmented Generation-based Chatbots, by Rama Akkiraju et al.
FACTS About Building Retrieval Augmented Generation-based Chatbots
by Rama Akkiraju, Anbang Xu, Deepak Bora, Tan Yu, Lu An, Vishal Seth, Aaditya Shukla, Pritam Gundecha, Hridhay Mehta, Ashwin Jha, Prithvi Raj, Abhinav Balasubramanian, Murali Maram, Guru Muthusamy, Shivakesh Reddy Annepally, Sidney Knowles, Min Du, Nick Burnett, Sean Javiya, Ashok Marannan, Mamta Kumari, Surbhi Jha, Ethan Dereszenski, Anupam Chakraborty, Subhash Ranjan, Amina Terfai, Anoop Surya, Tracey Mercer, Vinodh Kumar Thanigachalam, Tamar Bar, Sanjana Krishnan, Samy Kilaru, Jasmine Jaksic, Nave Algarici, Jacob Liberman, Joey Conway, Sonu Nayyar, Justin Boitano
First submitted to arxiv on: 10 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computation and Language (cs.CL)
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 This research proposes a framework for building effective enterprise chatbots powered by generative AI, specifically focusing on Retrieval Augmented Generation (RAG) and Large Language Models (LLMs). The study highlights the challenges of creating these chatbots, requiring meticulous pipeline engineering, including fine-tuning embeddings and LLMs, extracting documents from vector databases, rephrasing queries, and designing prompts. The authors introduce the FACTS framework, presenting fifteen RAG pipeline control points and empirical results on accuracy-latency tradeoffs between large and small LLMs. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Building chatbots that can help employees is a new way to make work easier. This paper talks about how to make these chatbots better. It’s hard because you need to make sure the chatbot is good at understanding what people say, finding the right answers, and being safe with personal information. The researchers came up with a plan to make it easier to build these chatbots, including some specific steps to follow and tools to use. |
Keywords
* Artificial intelligence * Fine tuning * Rag * Retrieval augmented generation
