Related papers: Improving Counterfactual Generation for Fair Hate …
This paper evaluates data augmentation and feature enhancement techniques for hate speech detection, comparing traditional classifiers, e.g., Delta Term Frequency-Inverse Document Frequency (Delta TF-IDF), with transformer-based models…
Generative models unfairly penalize data belonging to minority classes, suffer from model autophagy disorder (MADness), and learn biased estimates of the underlying distribution parameters. Our theoretical and empirical results show that…
Harmful content detection models tend to have higher false positive rates for content from marginalized groups. In the context of marginal abuse modeling on Twitter, such disproportionate penalization poses the risk of reduced visibility,…
The fairness and trustworthiness of Large Language Models (LLMs) are receiving increasing attention. Implicit hate speech, which employs indirect language to convey hateful intentions, occupies a significant portion of practice. However,…
Researchers have devised numerous ways to quantify social biases vested in pretrained language models. As some language models are capable of generating coherent completions given a set of textual prompts, several prompting datasets have…
With the rise of online hate speech, automatic detection of Hate Speech, Offensive texts as a natural language processing task is getting popular. However, very little research has been done to detect unintended social bias from these toxic…
Detecting hate speech in non-direct forms, such as irony, sarcasm, and innuendos, remains a persistent challenge for social networks. Although sarcasm and hate speech are regarded as distinct expressions, our work explores whether…
Automatic counterspeech generation methods have been developed to assist efforts in combating hate speech. Existing research focuses on generating counterspeech with linguistic attributes such as being polite, informative, and…
Machine learning algorithms in socially sensitive domains (e.g., credit decisions) often focus on equalizing predictive outcomes. However, satisfying these metrics does not guarantee that models use the same reasoning for different groups.…
Graph Neural Networks (GNNs) have been successful in modeling graph-structured data. However, similar to other machine learning models, GNNs can exhibit bias in predictions based on attributes like race and gender. Moreover, bias in GNNs…
To tackle the rising phenomenon of hate speech, efforts have been made towards data curation and analysis. When it comes to analysis of bias, previous work has focused predominantly on race. In our work, we further investigate bias in hate…
Current pre-trained language models have enabled remarkable improvements in downstream tasks, but it remains difficult to distinguish effects of statistical correlation from more systematic logical reasoning grounded on the understanding of…
Detecting gender-based hate speech in Indonesian social media remains challenging due to limited labeled datasets. While binary hate speech classification has advanced, a more granular category like gender-targeted hate speech is…
In current hate speech datasets, there exists a high correlation between annotators' perceptions of toxicity and signals of African American English (AAE). This bias in annotated training data and the tendency of machine learning models to…
Open-generation bias benchmarks evaluate social biases in Large Language Models (LLMs) by analyzing their outputs. However, the classifiers used in analysis often have inherent biases, leading to unfair conclusions. This study examines such…
Hate speech detection has been the subject of high research attention, due to the scale of content created on social media. In spite of the attention and the sensitive nature of the task, privacy preservation in hate speech detection has…
Biased news contributes to societal polarization and is often reinforced by hostile reader comments, constituting a vital yet often overlooked aspect of news dissemination. Our study reveals that offensive comments support biased content,…
Counterfactual fairness requires that a person would have been classified in the same way by an AI or other algorithmic system if they had a different protected class, such as a different race or gender. This is an intuitive standard, as…
Many studies have revealed that word embeddings, language models, and models for specific downstream tasks in NLP are prone to social biases, especially gender bias. Recently these techniques have been gradually applied to automatic…
While strong progress has been made in image captioning over the last years, machine and human captions are still quite distinct. A closer look reveals that this is due to the deficiencies in the generated word distribution, vocabulary…