no code implementations • 8 May 2024 • Preetam Prabhu Srikar Dammu, Hayoung Jung, Anjali Singh, Monojit Choudhury, Tanushree Mitra
Large language models (LLMs) have emerged as an integral part of modern societies, powering user-facing applications such as personal assistants and enterprise applications like recruitment tools.
no code implementations • 12 Mar 2024 • Preetam Prabhu Srikar Dammu, Himanshu Naidu, Mouly Dewan, Youngmin Kim, Tanya Roosta, Aman Chadha, Chirag Shah
In the midst of widespread misinformation and disinformation through social media and the proliferation of AI-generated texts, it has become increasingly difficult for people to validate and trust information they encounter.
no code implementations • 3 Nov 2023 • Preetam Prabhu Srikar Dammu, Chirag Shah
This undesirable property is the root cause of the manifestation of spurious correlations, which render models unreliable and prone to failure in the presence of distribution shifts.
no code implementations • 30 Oct 2023 • Preetam Prabhu Srikar Dammu, Yunhe Feng, Chirag Shah
Our new method is able to (1) identify weak decision boundaries for such classes; (2) construct search queries for Google as well as text for generating images through DALL-E 2 and Stable Diffusion; and (3) show how these newly captured training samples could alleviate population bias issue.