Homepage
Open in app
Sign in
Get started
Data Science at Microsoft
Methods
Visualization
Engineering
Organization
Development
People
All
Evaluating RAG capabilities of Small Language Models
Evaluating RAG capabilities of Small Language Models
Measuring the feasibility of using an SLM instead of an LLM in RAG or chatbot applications
Lazaro Hurtado
Jun 24
Beginner’s guide to causal discovery: The what, the why, and the how
Beginner’s guide to causal discovery: The what, the why, and the how
A simple explanation with business applications and an example Python demo
Ganga Meghanath
Jun 3
The path to a golden dataset, or how to evaluate your RAG?
The path to a golden dataset, or how to evaluate your RAG?
By Sandip Kulkarni and Alexandra Savelieva
Saveale
May 20
Techniques for enhancing OCR accuracy by assessing image sharpness
Techniques for enhancing OCR accuracy by assessing image sharpness
Optical Character Recognition (OCR) technology has revolutionized the way we digitize text from images. However, one persistent challenge…
Monica Kadlay
May 13
Using causal inference to measure business impact after program launch
Using causal inference to measure business impact after program launch
Alternatives for when experimentation is not possible
Xikai Zhao
May 6
Trustworthiness of Generative AI: Reducing hallucinations and increasing transparency
Trustworthiness of Generative AI: Reducing hallucinations and increasing transparency
“I knew I had just seen the most important advance in technology since the graphical user interface.” — Bill Gates, about ChatGPT acing an…
Iswarya Murali
Apr 29
Introduction to image inpainting with a practical example from the e-commerce industry
Introduction to image inpainting with a practical example from the e-commerce industry
Image inpainting is the task of restoring missing or damaged regions of an image using information from the surrounding pixels. Image…
Karol Zak
Apr 22
Toward learning-capable LLM agents
Toward learning-capable LLM agents
Presenting the concept and design principles behind developing LLM agents that possess the capability to learn
James Nguyen
Apr 15
Can ChatGPT do crossword puzzles?
Can ChatGPT do crossword puzzles?
Testing whether ChatGPT is simply a stochastic parrot or a logical reasoner using LangChain
Ceren Altincekic
Apr 1
The power of AI in Power BI: A data scientist’s perspective
The power of AI in Power BI: A data scientist’s perspective
As a data scientist, I often work with and analyze large, complex datasets and then communicate the results to various stakeholders. This…
Amy R Gillespie
Mar 25
Perturbation analysis and LLMs: How sensitive are LLMs to their input?
Perturbation analysis and LLMs: How sensitive are LLMs to their input?
A perturbation is a small change to an initial reference point. For example, the calm waters of a river can become choppy if they encounter…
Daniel Ferguson
Mar 18
How to build a fine-tuned customer service chatbot with Python and OpenAI
How to build a fine-tuned customer service chatbot with Python and OpenAI
Step-by-step Instructions to optimize your AI chatbot for a specific customer support query dataset from Kaggle
Deepsha Menghani
Mar 11
Evaluating LLM systems: Metrics, challenges, and best practices
Evaluating LLM systems: Metrics, challenges, and best practices
A detailed consideration of approaches to evaluation and selection
Jane Huang
Mar 5
Demystifying the art of writing prompts
Demystifying the art of writing prompts
Engaging with a Large Language Model (LLM) like ChatGPT isn’t just typing words into a void — it’s more like initiating a dynamic…
Piyush Jain
Feb 27
Harnessing the power of Large Language Models: A comparative overview of LangChain, Semantic…
Harnessing the power of Large Language Models: A comparative overview of LangChain, Semantic…
Some strategies for developing applications empowered by LLMs
Jane Huang
Feb 20
Customer retention (Part 2 of 2): Framework architecture
Customer retention (Part 2 of 2): Framework architecture
By Yasmin Bokobza, Sharath Kumar Rangappa, Swarnim Narayan, and Kiran R
Yasmin Bokobza
Feb 13
How to prompt engineer
How to prompt engineer
Prompt engineering is the art and science of crafting natural language prompts that guide Large Language Models (LLMs) to produce the best…
Aditya Challapally
Feb 6
Customer retention (Part 1 of 2): Understanding the fundamentals
Customer retention (Part 1 of 2): Understanding the fundamentals
Customer Retention as a Service (CRaaS) as a unified and generic framework for both churn features and model building
Yasmin Bokobza
Jan 30
Responsible AI in action, Part 3: Tools to help
Responsible AI in action, Part 3: Tools to help
Resources available to help support us as we design, develop, and deploy AI safely and responsibly
Kate B
Jan 23
Challenges of building LLM apps, Part 3: Building platforms
Challenges of building LLM apps, Part 3: Building platforms
A journey to create a platform for generating summaries and themes from lists of threads using Large Language Models
Aditya Challapally
Jan 2
Github Copilot X will NOT replace developers
Github Copilot X will NOT replace developers
For the last six months or so, I have been using Github Copilot X and now I don’t think I can write code without it. It simplifies my work…
Bharat Ruparel
Dec 26, 2023
Responsible AI in action, Part 2: Complete an impact assessment
Responsible AI in action, Part 2: Complete an impact assessment
Identifying and assessing the potential risks and harms of an AI system
Kate B
Dec 12, 2023
Don’t guess — profile!
Don’t guess — profile!
Programming is the foundation of all software, ranging from basic conditional statements to sophisticated Artificial Intelligence (AI)…
Shay Amram
Dec 5, 2023
Responsible AI in action, Part 1: Get started
Responsible AI in action, Part 1: Get started
Reasons to care about responsible AI
Kate B
Nov 28, 2023
Spark: Core concepts and workload optimization
Spark: Core concepts and workload optimization
Some of the core concepts and capabilities of Spark can make a major difference in the outcome of any data science project involving the…
orentola
Nov 14, 2023
Introduction to clustering-based customer segmentation
Introduction to clustering-based customer segmentation
Customer segmentation is a key technique used in business and marketing analysis to help companies better understand the user base and…
Kaixin Wang
Nov 7, 2023
Challenges of building LLM apps, Part 2: Building Copilots
Challenges of building LLM apps, Part 2: Building Copilots
In our previous article on the challenges involved in shipping even a simple LLM feature, we delved into the formidable task of crafting…
Aditya Challapally
Oct 30, 2023
About Data Science at Microsoft
Latest Stories
Archive
About Medium
Terms
Privacy
Teams