相关论文: fairBERTs: Erasing Sensitive Information Through S…

This paper investigates the parameter space of machine learning (ML) algorithms in aggravating or mitigating fairness bugs. Data-driven software is increasingly applied in social-critical applications where ensuring fairness is of paramount…

Artificial intelligence and machine learning have significantly bolstered the technological world. This paper explores the potential of transfer learning in natural language processing focusing mainly on sentiment analysis. The models…

Language Models (LMs) have demonstrated exceptional performance across various Natural Language Processing (NLP) tasks. Despite these advancements, LMs can inherit and amplify societal biases related to sensitive attributes such as gender…

Transformer-based pre-trained language models have significantly improved the performance of various natural language processing (NLP) tasks in the recent years. While effective and prevalent, these models are usually prohibitively large…

Pre-trained Language Model (PLM) has become a representative foundation model in the natural language processing field. Most PLMs are trained with linguistic-agnostic pre-training tasks on the surface form of the text, such as the masked…

Recent studies have demonstrated that large pretrained language models (LLMs) such as BERT and GPT-2 exhibit biases in token prediction, often inherited from the data distributions present in their training corpora. In response, a number of…

Machine learning models often make predictions based on biased features such as gender, race, and other social attributes, posing significant fairness risks, especially in societal applications, such as hiring, banking, and criminal…

Within the current trend of Pretained Language Models (PLM), emerge more and more criticisms about the ethical andecological impact of such models. In this article, considering these critical remarks, we propose to focus on smallermodels,…

Over the recent years, large pretrained language models (LM) have revolutionized the field of natural language processing (NLP). However, while pretraining on general language has been shown to work very well for common language, it has…

Contextual pretrained language models, such as BERT (Devlin et al., 2019), have made significant breakthrough in various NLP tasks by training on large scale of unlabeled text re-sources.Financial sector also accumulates large amount of…

Recent literature has suggested the potential of using large language models (LLMs) to make classifications for tabular tasks. However, LLMs have been shown to exhibit harmful social biases that reflect the stereotypes and inequalities…

Large Language Models (LLMs) are increasingly leveraged for translation tasks but often fall short when translating inclusive language -- such as texts containing the singular 'they' pronoun or otherwise reflecting fair linguistic…

Machine learning models are widely adopted in scenarios that directly affect people. The development of software systems based on these models raises societal and legal concerns, as their decisions may lead to the unfair treatment of…

Recent advances in the development of large language models have resulted in public access to state-of-the-art pre-trained language models (PLMs), including Generative Pre-trained Transformer 3 (GPT-3) and Bidirectional Encoder…

Language Models (LMs) have been shown to inherit undesired biases that might hurt minorities and underrepresented groups if such systems were integrated into real-world applications without careful fairness auditing. This paper proposes…

LLMs have demonstrated remarkable performance across diverse applications, yet they inadvertently absorb spurious correlations from training data, leading to stereotype associations between biased concepts and specific social groups. These…

Pretrained language models (PLMs), such as GPT2, have achieved remarkable empirical performance in text generation tasks. However, pretrained on large-scale natural language corpora, the generated text from PLMs may exhibit social bias…

[Context and motivation] Incompleteness in natural-language requirements is a challenging problem. [Question/problem] A common technique for detecting incompleteness in requirements is checking the requirements against external sources.…

Large-scale language models such as BERT have achieved state-of-the-art performance across a wide range of NLP tasks. Recent studies, however, show that such BERT-based models are vulnerable facing the threats of textual adversarial…

The widespread adoption of large language models (LLMs) underscores the urgent need to ensure their fairness. However, LLMs frequently present dominant viewpoints while ignoring alternative perspectives from minority parties, resulting in…