Related papers: Identifying and Reducing Gender Bias in Word-Level…

Large language models(LLM) are pre-trained on extensive corpora to learn facts and human cognition which contain human preferences. However, this process can inadvertently lead to these models acquiring biases and stereotypes prevalent in…

Bolukbasi et al. (2016) presents one of the first gender bias mitigation techniques for word representations. Their method takes pre-trained word representations as input and attempts to isolate a linear subspace that captures most of the…

Multilingual representations embed words from many languages into a single semantic space such that words with similar meanings are close to each other regardless of the language. These embeddings have been widely used in various settings,…

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.…

As natural language processing methods are increasingly deployed in real-world scenarios such as healthcare, legal systems, and social science, it becomes necessary to recognize the role they potentially play in shaping social biases and…

Gender-bias stereotypes have recently raised significant ethical concerns in natural language processing. However, progress in detection and evaluation of gender bias in natural language understanding through inference is limited and…

Large Language Models (LLMs) have been shown to be biased in prior work, as they generate text that is in line with stereotypical views of the world or that is not representative of the viewpoints and values of historically marginalized…

The Word Embedding Association Test shows that GloVe and word2vec word embeddings exhibit human-like implicit biases based on gender, race, and other social constructs (Caliskan et al., 2017). Meanwhile, research on learning reusable text…

Gender prediction has typically focused on lexical and social network features, yielding good performance, but making systems highly language-, topic-, and platform-dependent. Cross-lingual embeddings circumvent some of these limitations,…

Many studies have revealed that word embeddings, language models, and models for specific downstream tasks in NLP are prone to social biases, especially gender bias. Recently these techniques have been gradually applied to automatic…

Social bias in machine learning has drawn significant attention, with work ranging from demonstrations of bias in a multitude of applications, curating definitions of fairness for different contexts, to developing algorithms to mitigate…

The task of image captioning implicitly involves gender identification. However, due to the gender bias in data, gender identification by an image captioning model suffers. Also, the gender-activity bias, owing to the word-by-word…

Machine translation systems with inadequate document understanding can make errors when translating dropped or neutral pronouns into languages with gendered pronouns (e.g., English). Predicting the underlying gender of these pronouns is…

Pre-trained language models have been successful on text classification tasks, but are prone to learning spurious correlations from biased datasets, and are thus vulnerable when making inferences in a new domain. Prior work reveals such…

Gender biases in language generation systems are challenging to mitigate. One possible source for these biases is gender representation disparities in the training and evaluation data. Despite recent progress in documenting this problem and…

Gender bias in language models has attracted sufficient attention because it threatens social justice. However, most of the current debiasing methods degraded the model's performance on other tasks while the degradation mechanism is still…

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…

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…

This work sets the ground for studying how explicit grammatical gender assignment in job titles can affect the results of automatic job ranking systems. We propose the usage of metrics for ranking comparison controlling for gender to…

In recent years, word embeddings have been widely used to measure biases in texts. Even if they have proven to be effective in detecting a wide variety of biases, metrics based on word embeddings lack transparency and interpretability. We…