Skip to content
Tiatra, LLCTiatra, LLC
Tiatra, LLC
Information Technology Solutions for Washington, DC Government Agencies
  • Home
  • About Us
  • Services
    • IT Engineering and Support
    • Software Development
    • Information Assurance and Testing
    • Project and Program Management
  • Clients & Partners
  • Careers
  • News
  • Contact
 
  • Home
  • About Us
  • Services
    • IT Engineering and Support
    • Software Development
    • Information Assurance and Testing
    • Project and Program Management
  • Clients & Partners
  • Careers
  • News
  • Contact

The trick to better answers from generative AI

Generative AI offers great potential as an interface for enabling users to query your data in unique ways to receive answers honed for their needs. For example, as query assistants, generative AI tools can help customers better navigate an extensive product knowledge base using a simple question-and-answer format.

But before using generative AI to answer questions about your data, it’s important to first evaluate the questions being asked.

That’s the advice Lucky Gunasekara, CEO and co-founder of Miso.ai, has for teams developing generative AI tools today.

Miso.ai is the vendor partner for the Smart Answers project here at CIO.com and four of our sister sites. Smart Answers uses generative AI to answer questions about articles published on CIO.com and Foundry websites Computerworld, CSO, InfoWorld, and Network World. Miso.ai also built a similar Answers project for IDG’s consumer technology websites PCWorld, Macworld, and TechHive.

Interested in how Smart Answers surfaces its insights, I asked Gunasekara to discuss more deeply Miso.ai’s approach to understanding and answering users’ questions.

Large language models (LLMs) “are actually much more naive than we may think,” Gunasekara says. For example, if asked a question with a strong opinion, an LLM will likely go off and look to cherry-pick data that confirms the opinion, even if available data shows the opinion is wrong. So, if asked “Why did Project X fail?”, an LLM might scare up a list of reasons why the project was bad — even if it was a success. And that’s not something you want a public-facing app to do.

Evaluating questions is a step typically missed in so-called RAG (retrieval augmented generation) applications, Gunasekara notes. RAG apps point an LLM to a specific body of data and tell it to answer questions based only on that data. 

Such apps usually follow this (somewhat simplified) pattern for setup:

  1. Split the existing data into chunks, because all the data would be too large to fit into a single LLM query. 
  2. Generate what are known as embeddings for each chunk, to represent the semantic meaning of that chunk as a string of numbers, and store them. Update as needed as data changes.

And then per question:

  1. Generate embeddings.  
  2. Find text chunks that are most similar in meaning to the question, using calculations based on the embeddings. 
  3. Feed the user’s question into an LLM and tell it to answer based solely on the most relevant chunks.

Here is where Gunasekara’s team takes a different approach, adding a step to check the question before searching for relevant information. “Instead of asking that question directly, we first ask if that assumption is correct,” explains Andy Hsieh, Miso CTO and co-founder.

In addition to checking assumptions inherent in questions, there are other ways to enhance the basic RAG pipeline to help improve results. Gunasekara advises going beyond the basics especially when moving from the experiment phase toward a production-worthy solution.

“There’s a lot of emphasis on ‘Get a vector database, do a RAG setup, and everything will work out of the box,’” Gunasekara says. “It’s a great way to get a proof of concept. But if you need to make an enterprise-grade service that doesn’t create unintended consequences, it’s always context, context, context.”

That can mean using other signals besides semantic meaning of text, such as recency and popularity. Gunasekara points to another project Miso is working on with a cooking website, deconstructing the question: “What’s the best bake-ahead cake for a party?”

“You need to separate out what you really need signals on” for the query, he says. “Make-ahead” cake means it doesn’t need to be served right away; “for a party” means it needs to serve more than a few people. Then there’s the issue of how an LLM can determine what recipes are “best.” That might mean using other website data, such as which recipes have the highest traffic, top reader rankings, or were awarded an editor’s pick — all of which is separate from finding and summarizing related text chunks.

“A lot of the sort of spooky magic of getting these things right is more in those context cues,” Gunasekara says.

And while quality of LLM is another important factor, Miso doesn’t believe it’s necessary to use the most highly rated and pricey commercial LLMs. Instead, Miso is fine-tuning Llama 2-based models for some client projects in part to keep costs down, and because some clients don’t want their data going off to a third-party. Miso is also doing so due to what Gunasekara calls “a huge ground force happening right now in open-source [LLMs].”

“Open source is really catching up,” Hsieh adds. “Open-source models are very, very close to surpassing GPT-4.”

Generative AI
Read More from This Article: The trick to better answers from generative AI
Source: News

Category: NewsFebruary 29, 2024
Tags: art

Post navigation

PreviousPrevious post:Captive centers are back. Is DIY offshoring right for you?NextNext post:How to succeed at digital transformation in India

Related posts

Barb Wixom and MIT CISR on managing data like a product
May 30, 2025
Avery Dennison takes culture-first approach to AI transformation
May 30, 2025
The agentic AI assist Stanford University cancer care staff needed
May 30, 2025
Los desafíos de la era de la ‘IA en todas partes’, a fondo en Data & AI Summit 2025
May 30, 2025
“AI 비서가 팀 단위로 지원하는 효과”···퍼플렉시티, AI 프로젝트 10분 완성 도구 ‘랩스’ 출시
May 30, 2025
“ROI는 어디에?” AI 도입을 재고하게 만드는 실패 사례
May 30, 2025
Recent Posts
  • Barb Wixom and MIT CISR on managing data like a product
  • Avery Dennison takes culture-first approach to AI transformation
  • The agentic AI assist Stanford University cancer care staff needed
  • Los desafíos de la era de la ‘IA en todas partes’, a fondo en Data & AI Summit 2025
  • “AI 비서가 팀 단위로 지원하는 효과”···퍼플렉시티, AI 프로젝트 10분 완성 도구 ‘랩스’ 출시
Recent Comments
    Archives
    • May 2025
    • April 2025
    • March 2025
    • February 2025
    • January 2025
    • December 2024
    • November 2024
    • October 2024
    • September 2024
    • August 2024
    • July 2024
    • June 2024
    • May 2024
    • April 2024
    • March 2024
    • February 2024
    • January 2024
    • December 2023
    • November 2023
    • October 2023
    • September 2023
    • August 2023
    • July 2023
    • June 2023
    • May 2023
    • April 2023
    • March 2023
    • February 2023
    • January 2023
    • December 2022
    • November 2022
    • October 2022
    • September 2022
    • August 2022
    • July 2022
    • June 2022
    • May 2022
    • April 2022
    • March 2022
    • February 2022
    • January 2022
    • December 2021
    • November 2021
    • October 2021
    • September 2021
    • August 2021
    • July 2021
    • June 2021
    • May 2021
    • April 2021
    • March 2021
    • February 2021
    • January 2021
    • December 2020
    • November 2020
    • October 2020
    • September 2020
    • August 2020
    • July 2020
    • June 2020
    • May 2020
    • April 2020
    • January 2020
    • December 2019
    • November 2019
    • October 2019
    • September 2019
    • August 2019
    • July 2019
    • June 2019
    • May 2019
    • April 2019
    • March 2019
    • February 2019
    • January 2019
    • December 2018
    • November 2018
    • October 2018
    • September 2018
    • August 2018
    • July 2018
    • June 2018
    • May 2018
    • April 2018
    • March 2018
    • February 2018
    • January 2018
    • December 2017
    • November 2017
    • October 2017
    • September 2017
    • August 2017
    • July 2017
    • June 2017
    • May 2017
    • April 2017
    • March 2017
    • February 2017
    • January 2017
    Categories
    • News
    Meta
    • Log in
    • Entries feed
    • Comments feed
    • WordPress.org
    Tiatra LLC.

    Tiatra, LLC, based in the Washington, DC metropolitan area, proudly serves federal government agencies, organizations that work with the government and other commercial businesses and organizations. Tiatra specializes in a broad range of information technology (IT) development and management services incorporating solid engineering, attention to client needs, and meeting or exceeding any security parameters required. Our small yet innovative company is structured with a full complement of the necessary technical experts, working with hands-on management, to provide a high level of service and competitive pricing for your systems and engineering requirements.

    Find us on:

    FacebookTwitterLinkedin

    Submitclear

    Tiatra, LLC
    Copyright 2016. All rights reserved.