Related papers: A General Framework for Implicit and Explicit Debi…

Following the recent success of word embeddings, it has been argued that there is no such thing as an ideal representation for words, as different models tend to capture divergent and often mutually incompatible aspects like…

With the growing adoption of Text-to-Image (TTI) systems, the social biases of these models have come under increased scrutiny. Herein we conduct a systematic investigation of one such source of bias for diffusion models: embedding spaces.…

Many machine learning algorithms are trained and evaluated by splitting data from a single source into training and test sets. While such focus on in-distribution learning scenarios has led to interesting advancement, it has not been able…

Word embeddings are real-valued word representations able to capture lexical semantics and trained on natural language corpora. Models proposing these representations have gained popularity in the recent years, but the issue of the most…

Recently, implicit representation models, such as embedding or deep learning, have been successfully adopted to text classification task due to their outstanding performance. However, these approaches are limited to small- or moderate-scale…

Social scientists have recently turned to analyzing text using tools from natural language processing like word embeddings to measure concepts like ideology, bias, and affinity. However, word embeddings are difficult to use in the…

Neural embeddings are a popular set of methods for representing words, phrases or text as a low dimensional vector (typically 50-500 dimensions). However, it is difficult to interpret these dimensions in a meaningful manner, and creating…

Embeddings are functions that map raw input data to low-dimensional vector representations, while preserving important semantic information about the inputs. Pre-training embeddings on a large amount of unlabeled data and fine-tuning them…

Embedding-based similarity metrics between text sequences can be influenced not just by the content dimensions we most care about, but can also be biased by spurious attributes like the text's source or language. These document confounders…

Distributional semantics creates vector-space representations that capture many forms of semantic similarity, but their relation to semantic entailment has been less clear. We propose a vector-space model which provides a formal foundation…

Textual data used to train large language models (LLMs) exhibits multifaceted bias manifestations encompassing harmful language and skewed demographic distributions. Regulations such as the European AI Act require identifying and mitigating…

Distributional word representation methods exploit word co-occurrences to build compact vector encodings of words. While these representations enjoy widespread use in modern natural language processing, it is unclear whether they accurately…

Multiple measures, such as WEAT or MAC, attempt to quantify the magnitude of bias present in word embeddings in terms of a single-number metric. However, such metrics and the related statistical significance calculations rely on treating…

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…

Due to the implement of guardrails by developers, Large language models (LLMs) have demonstrated exceptional performance in explicit bias tests. However, bias in LLMs may occur not only explicitly, but also implicitly, much like humans who…

With the introduction of (large) language models, there has been significant concern about the unintended bias such models may inherit from their training data. A number of studies have shown that such models propagate gender stereotypes,…

Acoustics-to-word models are end-to-end speech recognizers that use words as targets without relying on pronunciation dictionaries or graphemes. These models are notoriously difficult to train due to the lack of linguistic knowledge. It is…

With the recent surge in social applications relying on knowledge graphs, the need for techniques to ensure fairness in KG based methods is becoming increasingly evident. Previous works have demonstrated that KGs are prone to various social…

The rapid developments of various machine learning models and their deployments in several applications has led to discussions around the importance of looking beyond the accuracies of these models. Fairness of such models is one such…

In the present paper we show that distributional information is particularly important when considering concept availability under implicit language learning conditions. Based on results from different behavioural experiments we argue that…