Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
CARE: Extracting Experimental Findings From Clinical Literature
Extracting fine-grained experimental findings from literature can provide dramatic utility for scientific applications. Prior work has developed annotation schemas and datasets for limited aspects…
A Legal Risk Taxonomy for Generative Artificial Intelligence
For the first time, this paper presents a taxonomy of legal risks associated with generative AI (GenAI) by breaking down complex legal concepts to provide a common understanding of potential legal…
Estimating the Causal Effect of Early ArXiving on Paper Acceptance
What is the effect of releasing a preprint of a paper before it is submitted for peer review? No randomized controlled trial has been conducted, so we turn to observational data to answer this…
The precipitation response to warming and CO2 increase: A comparison of a global storm resolving model and CMIP6 models.
Global storm-resolving models (GSRMs) can explicitly resolve some of deep convection are now being integrated for climate timescales. GSRMs are able to simulate more realistic precipitation…
RewardBench: Evaluating Reward Models for Language Modeling
Reward models (RMs) are at the crux of successfully using RLHF to align pretrained models to human preferences, yet there has been relatively little study that focuses on evaluation of those models.…
FigurA11y: AI Assistance for Writing Scientific Alt Text
High-quality alt text is crucial for making scientific figures accessible to blind and low-vision readers. Crafting complete, accurate alt text is challenging even for domain experts, as published…
Emulation of cloud microphysics in a climate model
We present a machine learning based emulator of a microphysics scheme for condensation and precipitation processes (Zhao-Carr) used operationally in a global atmospheric forecast model (FV3GFS). Our…
Closing the Curious Case of Neural Text Degeneration
Despite their ubiquity in language generation, it remains unknown why truncation sampling heuristics like nucleus sampling are so effective. We provide a theoretical explanation for the…
A machine learning parameterization of clouds in a coarse-resolution climate model for unbiased radiation
Coarse-grid weather and climate models rely particularly on parameterizations of cloud fields, and coarse-grained cloud fields from a fine-grid reference model are a natural target for a…
Enhancing Systematic Decompositional Natural Language Inference Using Informal Logic
Contemporary language models enable new opportunities for structured reasoning with text, such as the construction and evaluation of intuitive, proof-like textual entailment trees without relying on…