nlp

Overview of the Shared Task on Machine Translation Gender Bias Evaluation with Multilingual Holistic Bias

We describe the details of the Shared Task of the 5th ACL Workshop on Gender Bias in Natural Language Processing (GeBNLP 2024). The task uses dataset to investigate the quality of Machine Translation systems on a particular case of gender robustness. …

Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP)

This volume contains the proceedings of the Fifth Workshop on Gender Bias in Natural Language Processing held in conjunction with the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024).

Proceedings of the 8th Workshop on Online Abuse and Harms (WOAH 2024)

Digital technologies have brought many benefits for society, transforming how people connect, communicate and interact with each other. However, they have also enabled abusive and harmful content such as hate speech and harassment to reach large audiences, and for their negative effects to be amplified. The sheer amount of content shared online means that abuse and harm can only be tackled at scale with the help of computational tools. However, detecting and moderating online abuse and harms is a difficult task, with many technical, social, legal and ethical challenges. The Workshop on Online Harms and Abuse (WOAH) is the leading workshop dedicated to research addressing these challenges.

FairBelief - Assessing Harmful Beliefs in Language Models

Language Models (LMs) have been shown to inherit undesired biases that might hurt minorities and underrepresented groups if such systems were integrated into real-world applications without careful fairness auditing.This paper proposes FairBelief, an …

A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation

Recent instruction fine-tuned models can solve multiple NLP tasks when prompted to do so, with machine translation (MT) being a prominent use case. However, current research often focuses on standard performance benchmarks, leaving compelling …

Wisdom of Instruction-Tuned Language Model Crowds. Exploring Model Label Variation

Large Language Models (LLMs) exhibit remarkable text classification capabilities, excelling in zero- and few-shot learning (ZSL and FSL) scenarios. However, since they are trained on different datasets, performance varies widely across tasks between …

A Multi-dimensional study on Bias in Vision-Language models

In recent years, joint Vision-Language (VL) models have increased in popularity and capability. Very few studies have attempted to investigate bias in VL models, even though it is a well-known issue in both individual modalities.This paper presents …