English
Related papers

Related papers: Semantic and Structural Analysis of Implicit Biase…

200 papers

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…

Computation and Language · Computer Science 2024-04-04 Katrin Erk , Marianna Apidianaki

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…

Computation and Language · Computer Science 2022-05-25 Afra Feyza Akyürek , Muhammed Yusuf Kocyigit , Sejin Paik , Derry Wijaya

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…

Computation and Language · Computer Science 2025-06-18 Erik Derner , Sara Sansalvador de la Fuente , Yoan Gutiérrez , Paloma Moreda , Nuria Oliver

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…

Computation and Language · Computer Science 2025-01-08 Aishik Rakshit , Smriti Singh , Shuvam Keshari , Arijit Ghosh Chowdhury , Vinija Jain , Aman Chadha

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…

Computation and Language · Computer Science 2025-12-30 Lake Yin , Fan Huang

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…

Machine Learning · Computer Science 2024-10-07 Hamed Behzadi-Khormouji , José Oramas

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)…

Computation and Language · Computer Science 2020-01-06 Anne Lauscher , Goran Glavaš , Simone Paolo Ponzetto , Ivan Vulić

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…

Social and Information Networks · Computer Science 2019-06-03 Bo Wang , Baixiang Xue , Anthony G. Greenwald

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…

Machine Learning · Computer Science 2025-07-09 Sofiia Chorna , Kateryna Tarelkina , Eloïse Berthier , Gianni Franchi

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,…

Cryptography and Security · Computer Science 2024-10-10 Yukun Jiang , Zheng Li , Xinyue Shen , Yugeng Liu , Michael Backes , Yang Zhang

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…

Computer Vision and Pattern Recognition · Computer Science 2022-08-02 Ahmad Mustapha , Wael Khreich , Wes Masri

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…

Computation and Language · Computer Science 2023-08-17 Lisa Bauer , Karthik Gopalakrishnan , Spandana Gella , Yang Liu , Mohit Bansal , Dilek Hakkani-Tur

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…

Computation and Language · Computer Science 2025-06-10 Lance Calvin Lim Gamboa , Mark Lee

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…

Computation and Language · Computer Science 2025-04-14 Miguel López-Otal , Jorge Gracia , Jordi Bernad , Carlos Bobed , Lucía Pitarch-Ballesteros , Emma Anglés-Herrero

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…

Computation and Language · Computer Science 2024-08-28 Atmika Gorti , Manas Gaur , Aman Chadha

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…

Machine Learning · Computer Science 2024-12-06 Vito Paolo Pastore , Massimiliano Ciranni , Davide Marinelli , Francesca Odone , Vittorio Murino

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…

Computers and Society · Computer Science 2023-11-03 Qichao Wang , Tian Bian , Yian Yin , Tingyang Xu , Hong Cheng , Helen M. Meng , Zibin Zheng , Liang Chen , Bingzhe Wu

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…

Computation and Language · Computer Science 2024-05-07 Michael Burnham

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,…

Computation and Language · Computer Science 2026-04-09 Nandini Arimanda , Achyuth Mukund , Sakthi Balan Muthiah , Rajesh Sharma

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…

Computation and Language · Computer Science 2025-02-25 Yuxin Wang , Xiaomeng Zhu , Weimin Lyu , Saeed Hassanpour , Soroush Vosoughi