相关论文: Interpretable Debiasing of Vision-Language Models …

Vision-Language Models (VLMs) have achieved remarkable progress across tasks such as visual question answering and image captioning. Yet, the extent to which these models perform visual reasoning as opposed to relying on linguistic priors…

The burgeoning growth of open-sourced vision-language models (VLMs) has catalyzed a plethora of applications across diverse domains. Ensuring the transparency and interpretability of these models is critical for fostering trustworthy and…

Large Multimodal Models (LMMs) such as LLaVA are typically trained with an autoregressive language modeling objective, providing only indirect supervision to visual tokens. This often yields weak internal visual representations and brittle…

Deep learning models, particularly Convolutional Neural Networks (CNNs), have demonstrated exceptional performance in diagnosing skin diseases, often outperforming dermatologists. However, they have also unveiled biases linked to specific…

The advent of Large Language Models (LLMs) has significantly reshaped the trajectory of the AI revolution. Nevertheless, these LLMs exhibit a notable limitation, as they are primarily adept at processing textual information. To address this…

Sparse Autoencoders (SAEs) have emerged as a popular tool for interpreting the hidden states of large language models (LLMs). By learning to reconstruct activations from a sparse bottleneck layer, SAEs discover interpretable features from…

Vision-Language Models (VLMs) have demonstrated impressive capabilities across a range of tasks, yet concerns about their potential biases exist. This work investigates the extent to which prominent VLMs exhibit cultural biases by…

Deep neural networks are efficient at learning the data distribution if it is sufficiently sampled. However, they can be strongly biased by non-relevant factors implicitly incorporated in the training data. These include operational biases,…

Foundation Models (FMs) are rapidly transforming Affective Computing (AC), with Vision Language Models (VLMs) now capable of recognising emotions in zero shot settings. This paper probes a critical but underexplored question: what visual…

Societal biases are reflected in large pre-trained language models and their fine-tuned versions on downstream tasks. Common in-processing bias mitigation approaches, such as adversarial training and mutual information removal, introduce…

Deep neural networks (DNNs) are often prone to learn the spurious correlations between target classes and bias attributes, like gender and race, inherent in a major portion of training data (bias-aligned samples), thus showing unfair…

Debiasing language models from unwanted behaviors in Natural Language Understanding tasks is a topic with rapidly increasing interest in the NLP community. Spurious statistical correlations in the data allow models to perform shortcuts and…

Explaining Deep Learning models is becoming increasingly important in the face of daily emerging multimodal models, particularly in safety-critical domains like medical imaging. However, the lack of detailed investigations into the…

Machine learning (ML) algorithms play a critical role in decision-making across various domains, such as healthcare, finance, education, and law enforcement. However, concerns about fairness and bias in these systems have raised significant…

Vision-Language Models (VLMs) leverage aligned visual encoders to transform images into visual tokens, allowing them to be processed similarly to text by the backbone large language model (LLM). This unified input paradigm enables VLMs to…

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…

Vision-Language Models (VLMs) have demonstrated remarkable performance across a variety of real-world tasks. However, existing VLMs typically process visual information by serializing images, a method that diverges significantly from the…

Multilingual Pre-trained Language Models (MPLMs) have become essential tools for natural language processing. However, they often exhibit biases related to sensitive attributes such as gender, race, and religion. In this paper, we introduce…

Recent advances in visual-language machine learning models have demonstrated exceptional ability to use natural language and understand visual scenes by training on large, unstructured datasets. However, this training paradigm cannot…

Vision Language Models (VLMs) excel at identifying and describing objects but often fail at spatial reasoning. We study why VLMs, such as LLaVA, underutilize spatial cues despite having positional encodings and spatially rich vision encoder…