Latest Articles for Data Ethics

This study presents a new method for identifying key training images in AI-generated visuals.

Exploring techniques for reducing bias in advanced language models.

A new method tackles hidden threats in large language models.

This paper explores fairness and stability in machine learning models affected by their predictions.

This article discusses methods for improving AI alignment with various cultures.

Assessing strategies to manage copyright issues in language models.

This workshop analyzes gender stereotypes in AI through the lens of societal biases.

Improving how machines answer visual questions through structured reasoning.

A look at methods to reduce bias in automated decisions using Fair Representation Learning.

This paper discusses methods to reduce bias in AI image and text datasets.

FairPFN uses transformers to promote fairness in machine learning predictions.

New method examines how training data affects AI model outputs.

New index shows progress in AI model transparency among developers.

Examining credit attribution's role in machine learning and copyright issues.

Understanding the importance of auditing machine learning explanations for trust.

Selective debiasing aims to improve fairness in machine learning predictions.

This study addresses bias in image generation models by enhancing inclusivity.

This article reveals how VLMs reflect gender stereotypes in real-world tasks.

Research focuses on improving safety in large language models through alignment techniques.

PointNCBW offers a reliable way to verify ownership of point cloud datasets.

A study on improving methods for assessing Membership Inference Attacks in language models.

Explore the need for an open feedback system to improve AI responses.

A new method to generate unbiased synthetic data for AI applications.

New methods enhance how language models forget unwanted knowledge.

Introducing alterfactual explanations to enhance AI model transparency.

Examining the treatment of data workers in AI and its impact on fairness.

Examining the importance of fairness in AI systems impacting lives.

A new approach to valuing data emphasizes its uniqueness for machine learning.

Insights and guidance for responsible dataset creation in machine learning.

Examining how social factors influence machine learning outcomes in healthcare.

Exploring current gaps in data transparency practices across AI systems.

Examining the impact of AI and clinical credit systems on patient privacy and rights.

Explores the rise and impact of Foundation Models in artificial intelligence.

A framework to identify and reduce biases in visual data for AI models.

A new framework aims to uncover biases in role-playing scenarios of language models.

A new method aims to reduce bias in language models' predictions.

Developers can improve app privacy by better analyzing user reviews using advanced techniques.

A new approach tackles biases in image-text models effectively.

A project aims to give artists control over their creative contributions to AI.

Discover how emotional voice data is transforming speaker verification technology.