相关论文: Disentangling Dialect from Social Bias via Multita…

A recent spate of state-of-the-art semi- and un-supervised solutions disentangle and encode image "content" into a spatial tensor and image appearance or "style" into a vector, to achieve good performance in spatially equivariant tasks…

Large Language Models are increasingly used to simulate human opinion dynamics, yet the effect of genuine interaction is often obscured by systematic biases. We develop a Bayesian framework to disentangle and quantify three such biases: (i)…

Multilingual Large Language Models considerably changed how technologies influence language. While previous technologies could mediate or assist humans, there is now a tendency to offload the task of writing itself to these technologies,…

Text classifiers are applied at scale in the form of one-size-fits-all solutions. Nevertheless, many studies show that classifiers are biased regarding different languages and dialects. When measuring and discovering these biases, some gaps…

Text-to-image models are now easy to use and ubiquitous. However, prior work has found that they are prone to recapitulating harmful Western stereotypes. For example, requesting that a model generate an "African person and their house," may…

Natural language processing (NLP) systems have become a central technology in communication, education, medicine, artificial intelligence, and many other domains of research and development. While the performance of NLP methods has grown…

Deception, a prevalent aspect of human communication, has undergone a significant transformation in the digital age. With the globalization of online interactions, individuals are communicating in multiple languages and mixing languages on…

Since the advent of Federated Learning (FL), research has applied these methods to natural language processing (NLP) tasks. Despite a plethora of papers in FL for NLP, no previous works have studied how multilingual text impacts FL…

Cross-lingual transfer is a popular approach to increase the amount of training data for NLP tasks in a low-resource context. However, the best strategy to decide which cross-lingual data to include is unclear. Prior research often focuses…

Crowdsourcing has been the prevalent paradigm for creating natural language understanding datasets in recent years. A common crowdsourcing practice is to recruit a small number of high-quality workers, and have them massively generate…

Pre-trained language models (PLMs) are trained on data that inherently contains gender biases, leading to undesirable impacts. Traditional debiasing methods often rely on external corpora, which may lack quality, diversity, or demographic…

As language models (LMs) become increasingly powerful and widely used, it is important to quantify them for sociodemographic bias with potential for harm. Prior measures of bias are sensitive to perturbations in the templates designed to…

Speech Large Language Models (SpeechLLMs) process spoken input directly, retaining cues such as accent and perceived gender that were previously removed in cascaded pipelines. This introduces speaker identity dependent variation in…

Fairness and environmental impact are important research directions for the sustainable development of artificial intelligence. However, while each topic is an active research area in natural language processing (NLP), there is a surprising…

Emergent multi-agent communication protocols are very different from natural language and not easily interpretable by humans. We find that agents that were initially pretrained to produce natural language can also experience detrimental…

Bilingual and multilingual language models offer a promising path toward scaling NLP systems across diverse languages and users. However, their performance often varies wildly between languages as prior works show that adding more languages…

Large Language Models have garnered significant attention for their capabilities in multilingual natural language processing, while studies on risks associated with cross biases are limited to immediate context preferences. Cross-language…

Before being deployed for user-facing applications, developers align Large Language Models (LLMs) to user preferences through a variety of procedures, such as Reinforcement Learning From Human Feedback (RLHF) and Direct Preference…

Large language models (LLMs) are trained on vast, uncurated datasets that contain various forms of biases and language reinforcing harmful stereotypes that may be subsequently inherited by the models themselves. Therefore, it is essential…

Multilingual representations embed words from many languages into a single semantic space such that words with similar meanings are close to each other regardless of the language. These embeddings have been widely used in various settings,…