相关论文: How Gender Debiasing Affects Internal Model Repres…
The adoption of large language models (LLMs) is transforming the peer review process, from assisting reviewers in writing detailed evaluations to generating entire reviews automatically. While these capabilities offer new opportunities,…
An outtake from the findnings of a master thesis studying gender bias in course evaluations through the lense of machine learning and nlp. We use different methods to examine and explore the data and find differences in what students write…
Although large language models (LLMs) have demonstrated their effectiveness in a wide range of applications, they have also been observed to perpetuate unwanted biases present in the training data, potentially leading to harm for…
Many natural language inference (NLI) datasets contain biases that allow models to perform well by only using a biased subset of the input, without considering the remainder features. For instance, models are able to make a classification…
The influence of bias in datasets on the fairness of model predictions is a topic of ongoing research in various fields. We evaluate the performance of skin lesion classification using ResNet-based CNNs, focusing on patient sex variations…
In recent years, various methods have been proposed to evaluate gender bias in large language models (LLMs). A key challenge lies in the transferability of bias measurement methods initially developed for the English language when applied…
As Machine Learning models continue to be relied upon for making automated decisions, the issue of model bias becomes more and more prevalent. In this paper, we approach training a text classifica-tion model and optimize on bias…
This paper studies gender bias in machine translation through the lens of Large Language Models (LLMs). Four widely-used test sets are employed to benchmark various base LLMs, comparing their translation quality and gender bias against…
The rapid advancement of Large Language Models (LLMs) has sparked intense debate regarding the prevalence of bias in these models and its mitigation. Yet, as exemplified by both results on debiasing methods in the literature and reports of…
Neural Machine Translation systems built on top of Transformer-based architectures are routinely improving the state-of-the-art in translation quality according to word-overlap metrics. However, a growing number of studies also highlight…
AI systems frequently exhibit and amplify social biases, leading to harmful consequences in critical areas. This study introduces a novel encoder-decoder approach that leverages model gradients to learn a feature neuron encoding societal…
The pervasive spread of misinformation and disinformation in social media underscores the critical importance of detecting media bias. While robust Large Language Models (LLMs) have emerged as foundational tools for bias prediction,…
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…
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,…
Building equitable and inclusive NLP technologies demands consideration of whether and how social attitudes are represented in ML models. In particular, representations encoded in models often inadvertently perpetuate undesirable social…
Although large pre-trained language models have achieved great success in many NLP tasks, it has been shown that they reflect human biases from their pre-training corpora. This bias may lead to undesirable outcomes when these models are…
We investigate the potential for nationality biases in natural language processing (NLP) models using human evaluation methods. Biased NLP models can perpetuate stereotypes and lead to algorithmic discrimination, posing a significant…
Recent research in Natural Language Processing has revealed that word embeddings can encode social biases present in the training data which can affect minorities in real world applications. This paper explores the gender bias implicit in…
Neural machine translation inference procedures like beam search generate the most likely output under the model. This can exacerbate any demographic biases exhibited by the model. We focus on gender bias resulting from systematic errors in…
There has been significant prior work using templates to study bias against demographic attributes in MLMs. However, these have limitations: they overlook random variability of templates and target concepts analyzed, assume equality amongst…