相关论文: Mitigating Social Biases in Language Models throug…

Graph unlearning is a crucial approach for protecting user privacy by erasing the influence of user data on trained graph models. Recent developments in graph unlearning methods have primarily focused on maintaining model prediction…

Mitigating social bias in large language models (LLMs) has become an increasingly important research objective. However, existing debiasing methods often incur high human and computational costs, exhibit limited effectiveness, and struggle…

Large Language Models (LLMs) have revolutionized natural language processing, but their susceptibility to biases poses significant challenges. This comprehensive review examines the landscape of bias in LLMs, from its origins to current…

Machine unlearning aims to remove sensitive or undesired data from large language models. However, recent studies suggest that unlearning is often shallow, claiming that removed knowledge can easily be recovered. In this work, we critically…

State-of-the-art generative models exhibit powerful image-generation capabilities, introducing various ethical and legal challenges to service providers hosting these models. Consequently, Content Removal Techniques (CRTs) have emerged as a…

Vision-language models (VLMs) pre-trained on extensive datasets can inadvertently learn biases by correlating gender information with specific objects or scenarios. Current methods, which focus on modifying inputs and monitoring changes in…

Despite their impressive performance in a wide range of NLP tasks, Large Language Models (LLMs) have been reported to encode worrying-levels of gender biases. Prior work has proposed debiasing methods that require human labelled examples,…

Over the last year, Large Language Models (LLMs) like ChatGPT have become widely available and have exhibited fairness issues similar to those in previous machine learning systems. Current research is primarily focused on analyzing and…

While Code Language Models (CLMs) have demonstrated superior performance in software engineering tasks such as code generation and summarization, recent empirical studies reveal a critical privacy vulnerability: these models exhibit…

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…

Machine unlearning is a complex process that necessitates the model to diminish the influence of the training data while keeping the loss of accuracy to a minimum. Despite the numerous studies on machine unlearning in recent years, the…

Model robustness to bias is often determined by the generalization on carefully designed out-of-distribution datasets. Recent debiasing methods in natural language understanding (NLU) improve performance on such datasets by pressuring…

Machine learning methods adapt the parameters of a model, constrained to lie in a given model class, by using a fixed learning procedure based on data or active observations. Adaptation is done on a per-task basis, and retraining is needed…

Large language models (LLMs) have garnered significant attention for their remarkable performance in a continuously expanding set of natural language processing tasks. However, these models have been shown to harbor inherent societal…

To mitigate societal biases implicitly encoded in recent successful pretrained language models, a diverse array of approaches have been proposed to encourage model fairness, focusing on prompting, data augmentation, regularized fine-tuning,…

When a bilingual student learns to solve word problems in math, we expect the student to be able to solve these problem in both languages the student is fluent in,even if the math lessons were only taught in one language. However, current…

Computer vision models learn to perform a task by capturing relevant statistics from training data. It has been shown that models learn spurious age, gender, and race correlations when trained for seemingly unrelated tasks like activity…

As large language models (LLMs) have been used in many downstream tasks, the internal stereotypical representation may affect the fairness of the outputs. In this work, we introduce human knowledge into natural language interventions and…

We study the relationship between task-agnostic intrinsic and task-specific extrinsic social bias evaluation measures for Masked Language Models (MLMs), and find that there exists only a weak correlation between these two types of…

Large Vision-Language Models (LVLMs) have achieved strong performance on vision-language tasks, particularly Visual Question Answering (VQA). While prior work has explored unimodal biases in VQA, the problem of selection bias in…