Search Results for author: Kuleen Sasse

Found 2 papers, 0 papers with code

To Burst or Not to Burst: Generating and Quantifying Improbable Text

no code implementations27 Jan 2024 Kuleen Sasse, Samuel Barham, Efsun Sarioglu Kayi, Edward W. Staley

While large language models (LLMs) are extremely capable at text generation, their outputs are still distinguishable from human-authored text.

Text Generation

Selecting Shots for Demographic Fairness in Few-Shot Learning with Large Language Models

no code implementations14 Nov 2023 Carlos Aguirre, Kuleen Sasse, Isabel Cachola, Mark Dredze

In this work, we explore the effect of shots, which directly affect the performance of models, on the fairness of LLMs as NLP classification systems.

Fairness Few-Shot Learning +1

Cannot find the paper you are looking for? You can Submit a new open access paper.