Related papers: Text Style Transfer for Bias Mitigation using Mask…

The presence of specific linguistic signals particular to a certain sub-group can become highly salient to language models during training. In automated decision-making settings, this may lead to biased outcomes when models rely on cues…

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.…

Many studies have shown various biases targeting different demographic groups in language models, amplifying discrimination and harming fairness. Recent parameter modification debiasing approaches significantly degrade core capabilities…

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…

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…

Text-to-image diffusion models have been adopted into key commercial workflows, such as art generation and image editing. Characterising the implicit social biases they exhibit, such as gender and racial stereotypes, is a necessary first…

Language style transferring rephrases text with specific stylistic attributes while preserving the original attribute-independent content. One main challenge in learning a style transfer system is a lack of parallel data where the source…

We propose Masker, an unsupervised text-editing method for style transfer. To tackle cases when no parallel source-target pairs are available, we train masked language models (MLMs) for both the source and the target domain. Then we find…

Language style transfer is the problem of migrating the content of a source sentence to a target style. In many of its applications, parallel training data are not available and source sentences to be transferred may have arbitrary and…

Synthetic data offers a promising solution for mitigating data scarcity and demographic bias in mental health analysis, yet existing approaches largely rely on pretrained large language models (LLMs), which may suffer from limited output…

Vision-language models can encode societal biases and stereotypes, but there are challenges to measuring and mitigating these multimodal harms due to lacking measurement robustness and feature degradation. To address these challenges, we…

Text-based style transfer is a newly-emerging research topic that uses text information instead of style image to guide the transfer process, significantly extending the application scenario of style transfer. However, previous methods…

The representations in large language models contain multiple types of gender information. We focus on two types of such signals in English texts: factual gender information, which is a grammatical or semantic property, and gender bias,…

Abusive language detection models tend to have a problem of being biased toward identity words of a certain group of people because of imbalanced training datasets. For example, "You are a good woman" was considered "sexist" when trained on…

Large language models (LLMs) often inherit biases from vast amounts of training corpora. Traditional debiasing methods, while effective to some extent, do not completely eliminate memorized biases and toxicity in LLMs. In this paper, we…

Social media networks and chatting platforms often use an informal version of natural text. Adversarial spelling attacks also tend to alter the input text by modifying the characters in the text. Normalizing these texts is an essential step…

As language technologies gain prominence in real-world settings, it is important to understand how changes to language affect reader perceptions. This can be formalized as the causal effect of varying a linguistic attribute (e.g.,…

Due to their similarity-based learning objectives, pretrained sentence encoders often internalize stereotypical assumptions that reflect the social biases that exist within their training corpora. In this paper, we describe several kinds of…

Text style can reveal sensitive attributes of the author (e.g. race or age) to the reader, which can, in turn, lead to privacy violations and bias in both human and algorithmic decisions based on text. For example, the style of writing in…

Bias in textual data can lead to skewed interpretations and outcomes when the data is used. These biases could perpetuate stereotypes, discrimination, or other forms of unfair treatment. An algorithm trained on biased data may end up making…