相关论文: Gendec: A Machine Learning-based Framework for Gen…

Large Language Models (LLMs) are prone to generating content that exhibits gender biases, raising significant ethical concerns. Alignment, the process of fine-tuning LLMs to better align with desired behaviors, is recognized as an effective…

Machine learning models are trained to find patterns in data. NLP models can inadvertently learn socially undesirable patterns when training on gender biased text. In this work, we propose a general framework that decomposes gender bias in…

In recent years, large language models (LLM) have emerged as powerful tools for diverse natural language processing tasks. However, their potential for recommender systems under the generative recommendation paradigm remains relatively…

Masked Language Models (MLMs) pre-trained by predicting masked tokens on large corpora have been used successfully in natural language processing tasks for a variety of languages. Unfortunately, it was reported that MLMs also learn…

This article offers an empirical study on the different ways of encoding Chinese, Japanese, Korean (CJK) and English languages for text classification. Different encoding levels are studied, including UTF-8 bytes, characters, words,…

Machine learning model genealogy enables practitioners to determine which architectural family a neural network belongs to. In this paper, we introduce ShadowGenes, a novel, signature-based method for identifying a given model's…

Individual identification plays a pivotal role in ecology and ethology, notably as a tool for complex social structures understanding. However, traditional identification methods often involve invasive physical tags and can prove both…

The study of surnames as both linguistic and geographical markers of the past has proven valuable in several research fields spanning from biology and genetics to demography and social mobility. This article builds upon the existing…

Predicting nationality from personal names has practical value in marketing, demographic research, and genealogical studies. Conventional neural models learn statistical correspondences between names and nationalities from task-specific…

Motivation: In forensic or medico-legal investigation as well as in anthropology the gender determination of the subject (hit by a disastrous or any kind of traumatic situation) is mostly the first step. In state-of-the-art techniques the…

An individual's identity in a human society is specified by his or her name. Differently from family names, usually inherited from fathers, a given name for a child is often chosen at the parents' disposal. However, their decision cannot be…

Gender-inclusive language is important for achieving gender equality in languages with gender inflections, such as German. While stirring some controversy, it is increasingly adopted by companies and political institutions. A handful of…

We demonstrate an approach to face attribute detection that retains or improves attribute detection accuracy across gender and race subgroups by learning demographic information prior to learning the attribute detection task. The system,…

Each human genome is a 3 billion base pair set of encoding instructions. Decoding the genome using deep learning fundamentally differs from most tasks, as we do not know the full structure of the data and therefore cannot design…

In recent years, various methods have been proposed to evaluate gender bias in large language models (LLMs). A key challenge lies in the transferability of bias measurement methods initially developed for the English language when applied…

Is he/she my type or not? The answer to this question depends on the personal preferences of the one asking it. The individual process of obtaining a full answer may generally be difficult and time consuming, but often an approximate answer…

Besides its linguistic content, our speech is rich in biometric information that can be inferred by classifiers. Learning privacy-preserving representations for speech signals enables downstream tasks without sharing unnecessary, private…

State of the art Named Entity Recognition (NER) models have achieved an impressive ability to extract common phrases from text that belong to labels such as location, organization, time, and person. However, typical NER systems that rely on…

In recent times, there have been increasing accusations on artificial intelligence systems and algorithms of computer vision of possessing implicit biases. Even though these conversations are more prevalent now and systems are improving by…

Social biases reflected in language are inherently shaped by cultural norms, which vary significantly across regions and lead to diverse manifestations of stereotypes. Existing evaluations of social bias in large language models (LLMs) for…