3 citations · 5 across the 6 of their papers we have counts for
6 papers
Interpretability Can Be Actionable
Hadas Orgad, Fazl Barez, Tal Haklay +9
Interpretability aims to explain the behavior of deep neural networks. Despite rapid growth, there is mounting concern that much of this work has not translated into practical impa…
A Taxonomy of Transcendence
Natalie Abreu, Edwin Zhang, Eran Malach +1
Although language models are trained to mimic humans, the resulting systems display capabilities beyond the scope of any one person. To understand this phenomenon, we use a control…
Hidden Breakthroughs in Language Model Training
Sara Kangaslahti, Elan Rosenfeld, Naomi Saphra
Loss curves are smooth during most of model training, so visible discontinuities stand out as possible conceptual breakthroughs. Studying these breakthroughs enables a deeper under…
Fast Forwarding Low-Rank Training
Adir Rahamim, Naomi Saphra, Sara Kangaslahti +1
Parameter efficient finetuning methods like low-rank adaptation (LoRA) aim to reduce the computational costs of finetuning pretrained Language Models (LMs). Enabled by these low-ra…
ChatGPT Doesn't Trust Chargers Fans: Guardrail Sensitivity in Context
Victoria R. Li, Yida Chen, Naomi Saphra
While the biases of language models in production are extensively documented, the biases of their guardrails have been neglected. This paper studies how contextual information abou…
Transcendence: Generative Models Can Outperform The Experts That Train Them
Edwin Zhang, Vincent Zhu, Naomi Saphra +5
Generative models are trained with the simple objective of imitating the conditional probability distribution induced by the data they are trained on. Therefore, when trained on da…