相关论文: A Robust Bias Mitigation Procedure Based on the St…

Self-supervised sentence representation learning is the task of constructing an embedding space for sentences without relying on human annotation efforts. One straightforward approach is to finetune a pretrained language model (PLM) with a…

Text-to-image diffusion models, which are theoretically equivalent to score-based generative models, generate images through a multi-step denoising process guided by text embeddings extracted from pretrained vision-language models such as…

Concept Bottleneck Models (CBMs) have garnered increasing attention due to their ability to provide concept-based explanations for black-box deep learning models while achieving high final prediction accuracy using human-like concepts.…

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…

Cutting-edge image generation has been praised for producing high-quality images, suggesting a ubiquitous future in a variety of applications. However, initial studies have pointed to the potential for harm due to predictive bias,…

In this paper, we propose a new metric to measure the SOS bias in language models (LMs). Then, we validate the SOS bias and investigate the effectiveness of removing it. Finally, we investigate the impact of the SOS bias in LMs on their…

Image captioning model is a cross-modality knowledge discovery task, which targets at automatically describing an image with an informative and coherent sentence. To generate the captions, the previous encoder-decoder frameworks directly…

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…

For various speech-related tasks, confidence scores from a speech recogniser are a useful measure to assess the quality of transcriptions. In traditional hidden Markov model-based automatic speech recognition (ASR) systems, confidence…

In this paper, we address the limitations of existing text-to-image diffusion models in generating demographically fair results when given human-related descriptions. These models often struggle to disentangle the target language context…

In text recognition, self-supervised pre-training emerges as a good solution to reduce dependence on expansive annotated real data. Previous studies primarily focus on local visual representation by leveraging mask image modeling or…

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…

Texts in scene images convey critical information for scene understanding and reasoning. The abilities of reading and reasoning matter for the model in the text-based visual question answering (TextVQA) process. However, current TextVQA…

Concept Bottleneck Models (CBMs) aim to deliver interpretable and interventionable predictions by bridging features and labels with human-understandable concepts. While recent CBMs show promising potential, they suffer from information…

Large language models (LLMs) have demonstrated remarkable capabilities in simulating human behaviour and social intelligence. However, they risk perpetuating societal biases, especially when demographic information is involved. We introduce…

Safety-aligned large language models (LLMs) are becoming increasingly widespread, especially in sensitive applications where fairness is essential and biased outputs can cause significant harm. However, evaluating the fairness of models is…

Word embeddings are often criticized for capturing undesirable word associations such as gender stereotypes. However, methods for measuring and removing such biases remain poorly understood. We show that for any embedding model that…

Sensitive attributes are legally protected characteristics that should not be used to discriminate. Careful steps have been taken to minimize the risk of human bias regarding these fields, such as race and age. Large language models (LLMs)…

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…

Embedding-based similarity metrics between text sequences can be influenced not just by the content dimensions we most care about, but can also be biased by spurious attributes like the text's source or language. These document confounders…