Related papers: On the Unintended Social Bias of Training Language…

Gender, race and social biases have recently been detected as evident examples of unfairness in applications of Natural Language Processing. A key path towards fairness is to understand, analyse and interpret our data and algorithms. Recent…

Artificial Intelligence has the capacity to amplify and perpetuate societal biases and presents profound ethical implications for society. Gender bias has been identified in the context of employment advertising and recruitment tools, due…

Detecting and mitigating harmful biases in modern language models are widely recognized as crucial, open problems. In this paper, we take a step back and investigate how language models come to be biased in the first place. We use a…

Recent studies have shown that generative language models often reflect and amplify societal biases in their outputs. However, these studies frequently conflate observed biases with other task-specific shortcomings, such as comprehension…

Natural language generation models reproduce and often amplify the biases present in their training data. Previous research explored using sequence-to-sequence rewriting models to transform biased model outputs (or original texts) into more…

The presence of social biases in large language models (LLMs) has become a significant concern in AI research. These biases, often embedded in training data, can perpetuate harmful stereotypes and distort decision-making processes. When…

Generative Language Models (GLMs) have the potential to significantly shape our linguistic landscape due to their expansive use in various digital applications. However, this widespread adoption might inadvertently trigger a…

Vast availability of text data has enabled widespread training and use of AI systems that not only learn and predict attributes from the text but also generate text automatically. However, these AI models also learn gender, racial and…

Dialogue systems play an increasingly important role in various aspects of our daily life. It is evident from recent research that dialogue systems trained on human conversation data are biased. In particular, they can produce responses…

Gender bias in artificial intelligence (AI) and natural language processing has garnered significant attention due to its potential impact on societal perceptions and biases. This research paper aims to analyze gender bias in Large Language…

Recently, researchers have made considerable improvements in dialogue systems with the progress of large language models (LLMs) such as ChatGPT and GPT-4. These LLM-based chatbots encode the potential biases while retaining disparities that…

As machine learning methods are deployed in real-world settings such as healthcare, legal systems, and social science, it is crucial to recognize how they shape social biases and stereotypes in these sensitive decision-making processes.…

Recent research demonstrates that word embeddings, trained on the human-generated corpus, have strong gender biases in embedding spaces, and these biases can result in the discriminative results from the various downstream tasks. Whereas…

Machine learning models are trained to find patterns in data. NLP models can inadvertently learn socially undesirable patterns when training on gender biased text. In this work, we propose a general framework that decomposes gender bias in…

Multilingual Neural Machine Translation architectures mainly differ in the amount of sharing modules and parameters among languages. In this paper, and from an algorithmic perspective, we explore if the chosen architecture, when trained…

Progress in natural language generation research has been shaped by the ever-growing size of language models. While large language models pre-trained on web data can generate human-sounding text, they also reproduce social biases and…

Women are often perceived as junior to their male counterparts, even within the same job titles. While there has been significant progress in the evaluation of gender bias in natural language processing (NLP), existing studies seldom…

We present a general approach towards controllable societal biases in natural language generation (NLG). Building upon the idea of adversarial triggers, we develop a method to induce societal biases in generated text when input prompts…

Generative AI, such as large language models, has undergone rapid development within recent years. As these models become increasingly available to the public, concerns arise about perpetuating and amplifying harmful biases in applications.…

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…