Related papers: Semantic and Structural Analysis of Implicit Biase…
Embedding spaces contain interpretable dimensions indicating gender, formality in style, or even object properties. This has been observed multiple times. Such interpretable dimensions are becoming valuable tools in different areas of…
Researchers have devised numerous ways to quantify social biases vested in pretrained language models. As some language models are capable of generating coherent completions given a set of textual prompts, several prompting datasets have…
Large language models (LLMs) often inherit and amplify social biases embedded in their training data. A prominent social bias is gender bias. In this regard, prior work has mainly focused on gender stereotyping bias - the association of…
Embeddings play a pivotal role in the efficacy of Large Language Models. They are the bedrock on which these models grasp contextual relationships and foster a more nuanced understanding of language and consequently perform remarkably on a…
As Large Language Models (LLMs) have risen in prominence over the past few years, there has been concern over the potential biases in LLMs inherited from the training data. Previous studies have examined how LLMs exhibit implicit bias, such…
Model Interpretation aims at the extraction of insights from the internals of a trained model. A common approach to address this task is the characterization of relevant features internally encoded in the model that are critical for its…
Distributional word vectors have recently been shown to encode many of the human biases, most notably gender and racial biases, and models for attenuating such biases have consequently been proposed. However, existing models and studies (1)…
Language is a popular resource to mine speakers' attitude bias, supposing that speakers' statements represent their bias on concepts. However, psychology studies show that people's explicit bias in statements can be different from their…
While concept-based interpretability methods have traditionally focused on local explanations of neural network predictions, we propose a novel framework and interactive tool that extends these methods into the domain of mechanistic…
Large vision-language models (LVLMs) have been rapidly developed and widely used in various fields, but the (potential) stereotypical bias in the model is largely unexplored. In this study, we present a pioneering measurement framework,…
Since early machine learning models, metrics such as accuracy and precision have been the de facto way to evaluate and compare trained models. However, a single metric number doesn't fully capture the similarities and differences between…
Prompting inputs with natural language task descriptions has emerged as a popular mechanism to elicit reasonably accurate outputs from large-scale generative language models with little to no in-context supervision. This also helps gain…
Work on bias in pretrained language models (PLMs) focuses on bias evaluation and mitigation and fails to tackle the question of bias attribution and explainability. We propose a novel metric, the $\textit{bias attribution score}$, which…
Language models based on the Transformer architecture achieve excellent results in many language-related tasks, such as text classification or sentiment analysis. However, despite the architecture of these models being well-defined, little…
Large Language Models (LLMs) are prone to inheriting and amplifying societal biases embedded within their training data, potentially reinforcing harmful stereotypes related to gender, occupation, and other sensitive categories. This issue…
It is widely recognized that deep neural networks are sensitive to bias in the data. This means that during training these models are likely to learn spurious correlations between data and labels, resulting in limited generalization…
The recent surge in the research of diffusion models has accelerated the adoption of text-to-image models in various Artificial Intelligence Generated Content (AIGC) commercial products. While these exceptional AIGC products are gaining…
This paper introduces "Semantic Scaling," a novel method for ideal point estimation from text. I leverage large language models to classify documents based on their expressed stances and extract survey-like data. I then use item response…
Large Language Models (LLMs) excel at human-like language generation but often embed and amplify implicit, intersectional biases, especially under persona-driven contexts. Existing bias audits rely on static, embedding-based tests (CEAT,…
Handling implicit language is essential for natural language processing systems to achieve precise text understanding and facilitate natural interactions with users. Despite its importance, the absence of a metric for accurately measuring…