相关论文: fairBERTs: Erasing Sensitive Information Through S…

Speech Emotion Recognition (SER) systems have growing applications in sensitive domains such as mental health and education, where biased predictions can cause harm. Traditional fairness metrics, such as Equalised Odds and Demographic…

Large Language Models (LLMs) have fundamentally transformed the field of natural language processing; however, their vulnerability to biases presents a notable obstacle that threatens both fairness and trust. This review offers an extensive…

Developing AI systems capable of nuanced ethical reasoning is critical as they increasingly influence human decisions, yet existing models often rely on superficial correlations rather than principled moral understanding. This paper…

Previous works on the fairness of toxic language classifiers compare the output of models with different identity terms as input features but do not consider the impact of other important concepts present in the context. Here, besides…

Large Language Models (LLMs) have revolutionized natural language processing, yet concerns persist regarding their tendency to reflect or amplify social biases. This study introduces a novel evaluation framework to uncover gender biases in…

Sentiment classification is an important process in understanding people's perception towards a product, service, or topic. Many natural language processing models have been proposed to solve the sentiment classification problem. However,…

Free-text crash narratives recorded in real-world crash databases have been shown to play a significant role in improving traffic safety. However, large-scale analyses remain difficult to implement as there are no documented tools that can…

As Large Language Models (LLMs) become increasingly powerful and accessible to human users, ensuring fairness across diverse demographic groups, i.e., group fairness, is a critical ethical concern. However, current fairness and bias…

Masked Language Modeling (MLM) is widely used to pretrain language models. The standard random masking strategy in MLM causes the pre-trained language models (PLMs) to be biased toward high-frequency tokens. Representation learning of rare…

Language models (LMs) are pretrained to imitate internet text, including content that would violate human preferences if generated by an LM: falsehoods, offensive comments, personally identifiable information, low-quality or buggy code, and…

Large pre-trained language models are widely used in the community. These models are usually trained on unmoderated and unfiltered data from open sources like the Internet. Due to this, biases that we see in platforms online which are a…

The widespread application of pre-trained language models (PLMs) in natural language processing (NLP) has led to increasing concerns about their explainability. Selective rationalization is a self-explanatory framework that selects…

Pre-training by language modeling has become a popular and successful approach to NLP tasks, but we have yet to understand exactly what linguistic capacities these pre-training processes confer upon models. In this paper we introduce a…

Recent work has explored how to train machine learning models which do not discriminate against any subgroup of the population as determined by sensitive attributes such as gender or race. To avoid disparate treatment, sensitive attributes…

Pre-trained language models such as BERT have been a key ingredient to achieve state-of-the-art results on a variety of tasks in natural language processing and, more recently, also in information retrieval.Recent research even claims that…

Despite the growing reliance on fairness benchmarks to evaluate language models, the datasets that underpin these benchmarks remain critically underexamined. This survey addresses that overlooked foundation by offering a comprehensive…

As Machine Learning technologies become increasingly used in contexts that affect citizens, companies as well as researchers need to be confident that their application of these methods will not have unexpected social implications, such as…

In recent years, the development of large pretrained language models, such as BERT and GPT, significantly improved information extraction systems on various tasks, including relation classification. State-of-the-art systems are highly…

We present FireBERT, a set of three proof-of-concept NLP classifiers hardened against TextFooler-style word-perturbation by producing diverse alternatives to original samples. In one approach, we co-tune BERT against the training data and…

Recently, leveraging pre-trained Transformer based language models in down stream, task specific models has advanced state of the art results in natural language understanding tasks. However, only a little research has explored the…