Categories: AI/ML News

Researchers create protocol to test AI debiasing methods

A research team led by Brock University has developed a way to help programmers evaluate the robustness of debiasing methods on language models such as ChatGPT, which help to distinguish between appropriate and inappropriate speech as artificial intelligence (AI) generates text.

Low-Rank Optimal Transport: Approximation, Statistics and Debiasing

The matching principles behind optimal transport (OT) play an increasingly important role in machine learning, a trend which can be observed when OT is used to disambiguate datasets in applications (e.g. single-cell genomics) or used to improve more complex methods (e.g. balanced attention in transformers or self-supervised learning). To scale…

October 12, 2022

In "FAANG"

Learning Bias-reduced Word Embeddings Using Dictionary Definitions

Pre-trained word embeddings, such as GloVe, have shown undesirable gender, racial, and religious biases. To address this problem, we propose DD-GloVe, a train-time debiasing algorithm to learn word embeddings by leveraging dictionary definitions. We introduce dictionary-guided loss functions that encourage word embeddings to be similar to their relatively neutral dictionary…

October 12, 2022

In "FAANG"