Divyansh Agarwal's research focuses on building LLMs for synthetic data generation, trust and safety in AI systems, and factuality in summarization. He has co-authored more than 20 publications at top AI conferences like EMNLP, NAACL, ICWSM etc., including 1st author contributions, and has 5+ patents with Salesforce. He works on building intelligent agentic AI applications that utilize RAG for customer incubation.
My expertise
LLMs for synthetic data generation, Factuality in summarization, LLMs for creative writing, Trust and Safe AI systems
When I'm not working
When I'm not writing I am going on long runs, and finding good food in the city.
Generative AI (GenAI) technologies are increasingly integrated into every part of our daily workflow, from drafting emails to generating and fixing code with large language models (LLMs) and agents. Ensuring the safety and…
AI-powered solutions like Salesforce CRM are revolutionizing customer engagement, streamlining workflows, and providing deeper insights into customer needs. However, with the rise of large language models (LLMs), new security challenges have emerged. One…
Tl;Dr: Salesforce AI Research and Tableau AI collaborated to build the Pulse insight summary feature, GA for all Tableau Cloud customers starting in early 2024. The feature combines the power of generative AI…
Tl;Dr: Salesforce AI Research and Tableau AI collaborated to build the Pulse insight summary feature, GA for all Tableau Cloud customers starting in early 2024. The feature combines the power of generative AI…
TL;DR: Slack is a powerful productivity tool that professionals and teams around the globe depend on to communicate and keep up with vital information at work, making async work efficient. However, with an…
