Related papers: Mitigating Biases in Language Models via Bias Unle…

Deep neural networks often rely on spurious correlations in training data, leading to biased or unfair predictions in safety-critical domains such as medicine and autonomous driving. While conventional bias mitigation typically requires…

Large language models (LLMs) have demonstrated impressive capabilities across a wide range of natural language processing tasks. However, their outputs often exhibit social biases, raising fairness concerns. Existing debiasing methods, such…

Machine learning models often learn to make predictions that rely on sensitive social attributes like gender and race, which poses significant fairness risks, especially in societal applications, such as hiring, banking, and criminal…

NLU models often exploit biases to achieve high dataset-specific performance without properly learning the intended task. Recently proposed debiasing methods are shown to be effective in mitigating this tendency. However, these methods rely…

Numerous debiasing techniques have been proposed to mitigate the gender bias that is prevalent in pretrained language models. These are often evaluated on datasets that check the extent to which the model is gender-neutral in its…

Denoising diffusion models have emerged as a dominant approach for image generation, however they still suffer from slow convergence in training and color shift issues in sampling. In this paper, we identify that these obstacles can be…

Existing studies on bias mitigation methods for large language models (LLMs) use diverse baselines and metrics to evaluate debiasing performance, leading to inconsistent comparisons among them. Moreover, their evaluations are mostly based…

Word embeddings trained on large corpora have shown to encode high levels of unfair discriminatory gender, racial, religious and ethnic biases. In contrast, human-written dictionaries describe the meanings of words in a concise, objective…

Large Language Models (LLMs) inherit societal biases from their training data, potentially leading to harmful or unfair outputs. While various techniques aim to mitigate these biases, their effects are often evaluated only along the…

Machine learning models have been shown to inherit biases from their training datasets. This can be particularly problematic for vision-language foundation models trained on uncurated datasets scraped from the internet. The biases can be…

Dialogue systems play an increasingly important role in various aspects of our daily life. It is evident from recent research that dialogue systems trained on human conversation data are biased. In particular, they can produce responses…

Pretrained language models have been shown to exhibit biases and social stereotypes. Prior work on debiasing these models has largely focused on modifying embedding spaces during pretraining, which is not scalable for large models.…

Machine unlearning aims to remove the influence of specific training samples from a trained model without full retraining. While prior work has largely focused on privacy-motivated settings, we recast unlearning as a general-purpose tool…

While preliminary findings indicate that multilingual LLMs exhibit reduced bias compared to monolingual ones, a comprehensive understanding of the effect of multilingual training on bias mitigation, is lacking. This study addresses this gap…

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…

Gender bias in language models has attracted sufficient attention because it threatens social justice. However, most of the current debiasing methods degraded the model's performance on other tasks while the degradation mechanism is still…

We study transfer learning for a linear regression task using several least-squares pretrained models that can be overparameterized. We formulate the target learning task as optimization that minimizes squared errors on the target dataset…

Mitigation of biases, such as language models' reliance on gender stereotypes, is a crucial endeavor required for the creation of reliable and useful language technology. The crucial aspect of debiasing is to ensure that the models preserve…

Unfair stereotypical biases (e.g., gender, racial, or religious biases) encoded in modern pretrained language models (PLMs) have negative ethical implications for widespread adoption of state-of-the-art language technology. To remedy for…

It is widely recognized that deep neural networks are sensitive to bias in the data. This means that during training these models are likely to learn spurious correlations between data and labels, resulting in limited generalization…