Causal machine learning (ML) offers flexible, data-driven methods for predicting treatment
outcomes including efficacy and toxicity, thereby supporting the assessment and safety of …

Multimodal machine learning is a vibrant multi-disciplinary research field that aims to design
computer agents with intelligent capabilities such as understanding, reasoning, and learning …

Through considerable effort and intuition, several recent works have reverse-engineered
nontrivial behaviors oftransformer models. This paper systematizes the mechanistic …

Ensuring alignment, which refers to making models behave in accordance with human
intentions [1, 2], has become a critical task before deploying large language models (LLMs) …

Many research questions in Earth and environmental sciences are inherently causal,
requiring robust analyses to establish whether and how changes in one variable cause …

Importance Nonrandomized studies using insurance claims databases can be analyzed to
produce real-world evidence on the effectiveness of medical products. Given the lack of …

Pre-trained language models can be surprisingly adept at tasks they were not explicitly
trained on, but how they implement these capabilities is poorly understood. In this paper, we …

The causal capabilities of large language models (LLMs) are a matter of significant debate,
with critical implications for the use of LLMs in societally impactful domains such as …

We study GPT-3, a recent large language model, using tools from cognitive psychology.
More specifically, we assess GPT-3's decision-making, information search, deliberation, and …

Language models demonstrate both quantitative improvement and new qualitative
capabilities with increasing scale. Despite their potentially transformative impact, these new …