521 citations · 696 across the 5 of their papers we have counts for
5 papers
EngThrive: Make It Fast and Easy to Do Great Work
Brian Houck, Tim Bozarth, David Liu +1
Frameworks such as SPACE, DevEx, and DORA established that developer productivity is inherently multidimensional, but left practitioners with a practical question: what should we m…
Steering Language Model Refusal with Sparse Autoencoders
Kyle O'Brien, David Majercak, Xavier Fernandes +7
Responsible deployment of language models requires mechanisms for refusing unsafe prompts while preserving model performance. While most approaches modify model weights through add…
Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine
Harsha Nori, Yin Tat Lee, Sheng Zhang +15
Generalist foundation models such as GPT-4 have displayed surprising capabilities in a wide variety of domains and tasks. Yet, there is a prevalent assumption that they cannot matc…
Capabilities of GPT-4 on Medical Challenge Problems
Harsha Nori, Nicholas King, Scott Mayer McKinney +2
Large language models (LLMs) have demonstrated remarkable capabilities in natural language understanding and generation across various domains, including medicine. We present a com…
Invariant Language Modeling
Maxime Peyrard, Sarvjeet Singh Ghotra, Martin Josifoski +5
Large pretrained language models are critical components of modern NLP pipelines. Yet, they suffer from spurious correlations, poor out-of-domain generalization, and biases. Inspir…