Related papers: Parameter-efficient Modularised Bias Mitigation vi…

Large Language Models (LLMs) have shown strong abilities in general language tasks, yet adapting them to specific domains remains a challenge. Current method like Domain Adaptive Pretraining (DAPT) requires costly full-parameter training…

In ultrasound (US) imaging, various types of adaptive beamforming techniques have been investigated to improve the resolution and contrast-to-noise ratio of the delay and sum (DAS) beamformers. Unfortunately, the performance of these…

Adaptive optimizers like AdamW apply uniform hyperparameters across all parameter groups, ignoring heterogeneous optimization dynamics across layers and modules. We address this limitation by proposing MetaAdamW - a new optimizer that…

Prioritizing fairness is of central importance in artificial intelligence (AI) systems, especially for those societal applications, e.g., hiring systems should recommend applicants equally from different demographic groups, and risk…

Diffusion models have shown exceptional scaling properties in the image synthesis domain, and initial attempts have shown similar benefits for applying diffusion to unconditional text synthesis. Denoising diffusion models attempt to…

Machine learning models automatically learn discriminative features from the data, and are therefore susceptible to learn strongly-correlated biases, such as using protected attributes like gender and race. Most existing bias mitigation…

Recently, textual information has been proved to play a positive role in recommendation systems. However, most of the existing methods only focus on representation learning of textual information in ratings, while potential selection bias…

We propose an adaptive learning procedure to learn patch-based image priors for image denoising. The new algorithm, called the Expectation-Maximization (EM) adaptation, takes a generic prior learned from a generic external database and…

Debiasing is a fundamental concept in high-dimensional statistics. While degrees-of-freedom adjustment is the state-of-the-art technique in high-dimensional linear regression, it is limited to i.i.d. samples and sub-Gaussian covariates.…

Adapter-based parameter-efficient transfer learning has achieved exciting results in vision-language models. Traditional adapter methods often require training or fine-tuning, facing challenges such as insufficient samples or resource…

Existing works show that augmenting the training data of pre-trained language models (PLMs) for classification tasks fine-tuned via parameter-efficient fine-tuning methods (PEFT) using both clean and adversarial examples can enhance their…

The recent success of neural machine translation models relies on the availability of high quality, in-domain data. Domain adaptation is required when domain-specific data is scarce or nonexistent. Previous unsupervised domain adaptation…

Large language models struggle to accumulate evidence across multiple rounds of user interaction, failing to update their beliefs in a manner consistent with Bayesian inference. Existing solutions require fine-tuning on sensitive user…

Multimodal recommendation focuses primarily on effectively exploiting both behavioral and multimodal information for the recommendation task. However, most existing models suffer from the following issues when fusing information from two…

Machine learning systems produce biased results towards certain demographic groups, known as the fairness problem. Recent approaches to tackle this problem learn a latent code (i.e., representation) through disentangled representation…

Though notable progress has been made, neural-based aspect-based sentiment analysis (ABSA) models are prone to learn spurious correlations from annotation biases, resulting in poor robustness on adversarial data transformations. Among the…

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…

The escalating integration of machine learning in high-stakes fields such as healthcare raises substantial concerns about model fairness. We propose an interpretable framework - Fairness-Aware Interpretable Modeling (FAIM), to improve model…

Although instruction tuning is widely used to adjust behavior in Large Language Models (LLMs), extensive empirical evidence and research indicates that it is primarily a process where the model fits to specific task formats, rather than…

As open-weight large language models (LLMs) achieve ever more impressive performances across a wide range of tasks in English, practitioners aim to adapt these models to different languages. However, such language adaptation is often…