相关论文: Easy Adaptation to Mitigate Gender Bias in Multili…

Speech-based AI models are emerging as powerful tools for detecting depression and the presence of Post-traumatic stress disorder (PTSD), offering a non-invasive and cost-effective way to assess mental health. However, these models often…

Pretrained multilingual models exhibit the same social bias as models processing English texts. This systematic review analyzes emerging research that extends bias evaluation and mitigation approaches into multilingual and non-English…

Studies in bias and fairness in natural language processing have primarily examined social biases within a single language and/or across few attributes (e.g. gender, race). However, biases can manifest differently across various languages…

This paper provides a comprehensive evaluation of demographic and linguistic biases in omnimodal language models that process text, images, audio, and video within a single framework. Although these models are being widely deployed, their…

Translating from languages without productive grammatical gender like English into gender-marked languages is a well-known difficulty for machines. This difficulty is also due to the fact that the training data on which models are built…

Image captioning models are known to perpetuate and amplify harmful societal bias in the training set. In this work, we aim to mitigate such gender bias in image captioning models. While prior work has addressed this problem by forcing…

This paper is focused on the finetuning of acoustic models for speaker adaptation goals on a given gender. We pretrained the Transformer baseline model on Librispeech-960 and conduct experiments with finetuning on the gender-specific test…

Discriminatory language and biases are often present in hate speech during conversations, which usually lead to negative impacts on targeted groups such as those based on race, gender, and religion. To tackle this issue, we propose an…

State-of-the-art approaches for hate-speech detection usually exhibit poor performance in out-of-domain settings. This occurs, typically, due to classifiers overemphasizing source-specific information that negatively impacts its domain…

We introduce a multilingual extension of the HOLISTICBIAS dataset, the largest English template-based taxonomy of textual people references: MULTILINGUALHOLISTICBIAS. This extension consists of 20,459 sentences in 50 languages distributed…

Large Language Models (LLMs) are prone to generating content that exhibits gender biases, raising significant ethical concerns. Alignment, the process of fine-tuning LLMs to better align with desired behaviors, is recognized as an effective…

When exposed to human-generated data, language models are known to learn and amplify societal biases. While previous works introduced benchmarks that can be used to assess the bias in these models, they rely on assumptions that may not be…

Classifiers tend to propagate biases present in the data on which they are trained. Hence, it is important to understand how the demographic identities of the annotators of comments affect the fairness of the resulting model. In this paper,…

The gender bias present in the data on which language models are pre-trained gets reflected in the systems that use these models. The model's intrinsic gender bias shows an outdated and unequal view of women in our culture and encourages…

Training data for NLP tasks often exhibits gender bias in that fewer sentences refer to women than to men. In Neural Machine Translation (NMT) gender bias has been shown to reduce translation quality, particularly when the target language…

Pre-trained language models encode undesirable social biases, which are further exacerbated in downstream use. To this end, we propose MABEL (a Method for Attenuating Gender Bias using Entailment Labels), an intermediate pre-training…

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…

Textual data used to train large language models (LLMs) exhibits multifaceted bias manifestations encompassing harmful language and skewed demographic distributions. Regulations such as the European AI Act require identifying and mitigating…

Domain adaptation approaches seek to learn from a source domain and generalize it to an unseen target domain. At present, the state-of-the-art unsupervised domain adaptation approaches for subjective text classification problems leverage…

It is common practice in text classification to only use one majority label for model training even if a dataset has been annotated by multiple annotators. Doing so can remove valuable nuances and diverse perspectives inherent in the…