- Published on May 7, 2023
- In AI Features
A Striking Relevance of Data Sketching in LLMs
Can data sketching be used in large language models for building chatbots?
- By Mohit Pandey
At Data Engineering Summit (DES) 2023, presenting a talk about Unleashing the Power of Probabilistic Data Structures: Optimizing Storage and Performance for Big Data, Sudarshan Pakrashi, Director of Data Engineering at Zeotap spoke about statistical algorithms designed to optimise use of memory in storing and querying large datasets. In one of the questions asked, he spoke about if data sketching can be used in current generative AI models such as LLMs.
To this, Pakrashi responded that it is possible to do so and is actually a “great analogy”. He explained how in every language model there are word associations that need to be maintained when there is a huge dataset of words. “Imagine the permutations and combinations that you want to have and sketches are in fact used to maintain
📣 Want to advertise in AIM? Book here
Mohit Pandey
Mohit writes about AI in simple, explainable, and often funny words. He's especially passionate about chatting with those building AI for Bharat, with the occasional detour into AGI.
Related Posts
Building an AI Economy That Includes Everyone
“What we’re seeing is that accessibility-driven design often solves a broader problem. It’s not charity. It’s engineering.”
Top 10 Companies That Crowned Hyderabad as India’s Greenfield GCC Leader in 2025
Telangana has attracted over 75 greenfield GCCs in 2025, compared with 40-plus in Karnataka.
The AI Coding Gold Rush Ends Where Harness Begins
“Only 30% of software engineering happens on the laptop. The real 70% starts after you commit the code,” says Jyoti
How Gradient-Boosting is Quietly Powering India’s Research Push
From groundwater and slopes to carbon sinks, tools like CatBoost are enabling Indian scientists to extract insights and drive sustainability.
India’s Data Centre Boom Is Running Into a Talent Wall
With capacity expected to more than double this decade, the industry is investing in training as graduates struggle to meet
This Firm Wants to be the ‘Next Big Disruptor’ in Networking
Arrcus positions itself as a horizontal software layer that can run across different types of networking hardware.
Will 2026 be the year of AI IPOs?
With CoreWeave’s listing and Fractal Analytics going for an IPO, an array of AI companies are now looking to raise
Fighting Deepfakes May Not Be a Technology Problem
Defenders must be active at all times, while attackers need only one opportunity.
Download the easiest way to
stay informed
stay informed
