Related papers: Language-guided Detection and Mitigation of Unknow…
We study fairness in supervised few-shot meta-learning models that are sensitive to discrimination (or bias) in historical data. A machine learning model trained based on biased data tends to make unfair predictions for users from minority…
Addressing biases in computer vision models is crucial for real-world AI deployments. However, mitigating visual biases is challenging due to their unexplainable nature, often identified indirectly through visualization or sample…
Many studies have shown various biases targeting different demographic groups in language models, amplifying discrimination and harming fairness. Recent parameter modification debiasing approaches significantly degrade core capabilities…
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…
Machine learning model bias can arise from dataset composition: correlated sensitive features can distort the downstream classification model's decision boundary and lead to performance differences along these features. Existing de-biasing…
A recent study has shown that large-scale visual datasets are very biased: they can be easily classified by modern neural networks. However, the concrete forms of bias among these datasets remain unclear. In this study, we propose a…
Recent works find that AI algorithms learn biases from data. Therefore, it is urgent and vital to identify biases in AI algorithms. However, the previous bias identification pipeline overly relies on human experts to conjecture potential…
Improperly constructed datasets can result in inaccurate inferences. For instance, models trained on biased datasets perform poorly in terms of generalization (i.e., dataset bias). Recent debiasing techniques have successfully achieved…
Models trained on real-world data often mirror and exacerbate existing social biases. Traditional methods for mitigating these biases typically require prior knowledge of the specific biases to be addressed, such as gender or racial biases,…
Many machine learning algorithms are trained and evaluated by splitting data from a single source into training and test sets. While such focus on in-distribution learning scenarios has led to interesting advancement, it has not been able…
Deep neural networks are highly susceptible to learning biases in visual data. While various methods have been proposed to mitigate such bias, the majority require explicit knowledge of the biases present in the training data in order to…
It is evident that deep text classification models trained on human data could be biased. In particular, they produce biased outcomes for texts that explicitly include identity terms of certain demographic groups. We refer to this type of…
Many datasets have been shown to contain incidental correlations created by idiosyncrasies in the data collection process. For example, sentence entailment datasets can have spurious word-class correlations if nearly all contradiction…
Neural networks are prone to be biased towards spurious correlations between classes and latent attributes exhibited in a major portion of training data, which ruins their generalization capability. We propose a new method for training…
Despite significant progress, recent studies indicate that current large language models (LLMs) may still capture dataset biases and utilize them during inference, leading to the poor generalizability of LLMs. However, due to the diversity…
Language models frequently inherit societal biases from their training data. Numerous techniques have been proposed to mitigate these biases during both the pre-training and fine-tuning stages. However, fine-tuning a pre-trained debiased…
Most machine learning methods are known to capture and exploit biases of the training data. While some biases are beneficial for learning, others are harmful. Specifically, image captioning models tend to exaggerate biases present in…
Societal biases present in pre-trained large language models are a critical issue as these models have been shown to propagate biases in countless downstream applications, rendering them unfair towards specific groups of people. Since…
Many datasets are underspecified: there exist multiple equally viable solutions to a given task. Underspecification can be problematic for methods that learn a single hypothesis because different functions that achieve low training loss can…
Large language models have revolutionized natural language processing with their surprising capability to understand and generate human-like text. However, many of these models inherit and further amplify the biases present in their…