Polaris: A Safety-focused LLM Constellation Architecture for Healthcare

no code implementations • 20 Mar 2024 • Subhabrata Mukherjee, Paul Gamble, Markel Sanz Ausin, Neel Kant, Kriti Aggarwal, Neha Manjunath, Debajyoti Datta, Zhengliang Liu, Jiayuan Ding, Sophia Busacca, Cezanne Bianco, Swapnil Sharma, Rae Lasko, Michelle Voisard, Sanchay Harneja, Darya Filippova, Gerry Meixiong, Kevin Cha, Amir Youssefi, Meyhaa Buvanesh, Howard Weingram, Sebastian Bierman-Lytle, Harpreet Singh Mangat, Kim Parikh, Saad Godil, Alex Miller

We train our models on proprietary data, clinical care plans, healthcare regulatory documents, medical manuals, and other medical reasoning documents.

GPT-4 Llama +1

Stochastic Code Generation

no code implementations • 14 Apr 2023 • Swapnil Sharma, Nikita Anand, Kranthi Kiran G. V

Large language models pre-trained for code generation can generate high-quality short code but often struggle with generating coherent long code and understanding higher-level or system-level specifications.

Code Generation Language Modelling +1

Evaluation of Social Biases in Recent Large Pre-Trained Models

no code implementations • 13 Apr 2023 • Swapnil Sharma, Nikita Anand, Kranthi Kiran G. V., Alind Jain

The results are compiled and we find that all the models under study do exhibit biases but have generally improved as compared to BERT.