Search Results for author: Susan Leavy

Found 10 papers, 3 papers with code

Inferring Gender: A Scalable Methodology for Gender Detection with Online Lexical Databases

1 code implementation LTEDI (ACL) 2022 Marion Bartl, Susan Leavy

This paper presents a new method for automatic detection of gendered terms in large-scale language datasets.

From 'Showgirls' to 'Performers': Fine-tuning with Gender-inclusive Language for Bias Reduction in LLMs

no code implementations5 Jul 2024 Marion Bartl, Susan Leavy

Gender bias is not only prevalent in Large Language Models (LLMs) and their training data, but also firmly ingrained into the structural aspects of language itself.

Biased Attention: Do Vision Transformers Amplify Gender Bias More than Convolutional Neural Networks?

1 code implementation15 Sep 2023 Abhishek Mandal, Susan Leavy, Suzanne Little

We examine bias amplification when models belonging to these two architectures are used as a part of large multimodal models, evaluating the different image encoders of Contrastive Language Image Pretraining which is an important model used in many generative models such as DALL-E and Stable Diffusion.

Image Classification

Industrial Memories: Exploring the Findings of Government Inquiries with Neural Word Embedding and Machine Learning

no code implementations2 Aug 2023 Susan Leavy, Emilie Pine, Mark T Keane

We present a text mining system to support the exploration of large volumes of text detailing the findings of government inquiries.

text-classification Text Classification

Curatr: A Platform for Semantic Analysis and Curation of Historical Literary Texts

no code implementations13 Jun 2023 Susan Leavy, Gerardine Meaney, Karen Wade, Derek Greene

The increasing availability of digital collections of historical and contemporary literature presents a wealth of possibilities for new research in the humanities.

Diversity Word Embeddings

Multimodal Composite Association Score: Measuring Gender Bias in Generative Multimodal Models

no code implementations26 Apr 2023 Abhishek Mandal, Susan Leavy, Suzanne Little

In this paper, we propose Multimodal Composite Association Score (MCAS) as a new method of measuring gender bias in multimodal generative models.

Inclusive Ethical Design for Recommender Systems

no code implementations13 Sep 2022 Susan Leavy

Recommender systems are becoming increasingly central as mediators of information with the potential to profoundly influence societal opinion.

Recommendation Systems

Towards Lexical Gender Inference: A Scalable Methodology using Online Databases

1 code implementation28 Jun 2022 Marion Bartl, Susan Leavy

and nouns with lexical gender ('mother', 'boyfriend', 'policewoman', etc.).

Uncovering Gender Bias in Media Coverage of Politicians with Machine Learning

no code implementations15 May 2020 Susan Leavy

This paper presents research uncovering systematic gender bias in the representation of political leaders in the media, using artificial intelligence.

BIG-bench Machine Learning

Mitigating Gender Bias in Machine Learning Data Sets

no code implementations14 May 2020 Susan Leavy, Gerardine Meaney, Karen Wade, Derek Greene

Artificial Intelligence has the capacity to amplify and perpetuate societal biases and presents profound ethical implications for society.

BIG-bench Machine Learning Fairness +1

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