3 papers
cs.LG2025
Aggregating Concepts of Fairness and Accuracy in Prediction Algorithms
David Kinney
An algorithm that outputs predictions about the state of the world will almost always be designed with the implicit or explicit goal of outputting accurate predictions (i.e., predi…
cs.CL2025
Towards Geo-Culturally Grounded LLM Generations
Piyawat Lertvittayakumjorn, David Kinney, Vinodkumar Prabhakaran +2
Generative large language models (LLMs) have demonstrated gaps in diverse cultural awareness across the globe. We investigate the effect of retrieval augmented generation and searc…
cs.LG2023
Loop Polarity Analysis to Avoid Underspecification in Deep Learning
Donald Martin, David Kinney
Deep learning is a powerful set of techniques for detecting complex patterns in data. However, when the causal structure of that process is underspecified, deep learning models can…