Related papers: GeniL: A Multilingual Dataset on Generalizing Lang…
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…
The rapid advancement of generative models has intensified the challenge of detecting and interpreting visual forgeries, necessitating robust frameworks for image forgery detection while providing reasoning as well as localization. While…
Human and model-generated texts can be distinguished by examining the magnitude of likelihood in language. However, it is becoming increasingly difficult as language model's capabilities of generating human-like texts keep evolving. This…
Combating online hate speech in multilingual settings requires approaches that go beyond English-centric models and capture the cultural and linguistic diversity of global online discourse. This paper presents a comprehensive survey and…
We present a systematic study of biases in natural language generation (NLG) by analyzing text generated from prompts that contain mentions of different demographic groups. In this work, we introduce the notion of the regard towards a…
As generative large language models (LLMs) grow more performant and prevalent, we must develop comprehensive enough tools to measure and improve their fairness. Different prompt-based datasets can be used to measure social bias across…
Hate speech is one type of harmful online content which directly attacks or promotes hate towards a group or an individual member based on their actual or perceived aspects of identity, such as ethnicity, religion, and sexual orientation.…
Machine learning models that convert user-written text descriptions into images are now widely available online and used by millions of users to generate millions of images a day. We investigate the potential for these models to amplify…
Generative spoken language models pretrained on large-scale raw audio can continue a speech prompt with appropriate content while preserving attributes like speaker and emotion, serving as foundation models for spoken dialogue. In prior…
With the proliferation of social media, there has been a sharp increase in offensive content, particularly targeting vulnerable groups, exacerbating social problems such as hatred, racism, and sexism. Detecting offensive language use is…
Digital dehumanization, although a critical issue, remains largely overlooked within the field of computational linguistics and Natural Language Processing. The prevailing approach in current research concentrating primarily on a single…
We introduce a multilingual extension of the HOLISTICBIAS dataset, the largest English template-based taxonomy of textual people references: MULTILINGUALHOLISTICBIAS. This extension consists of 20,459 sentences in 50 languages distributed…
A channel corresponds to a viewpoint or transformation of an underlying meaning. A pair of parallel sentences in English and French express the same underlying meaning, but through two separate channels corresponding to their languages. In…
This position paper discusses the problem of multilingual evaluation. Using simple statistics, such as average language performance, might inject linguistic biases in favor of dominant language families into evaluation methodology. We argue…
Bias mitigation approaches reduce models' dependence on sensitive features of data, such as social group tokens (SGTs), resulting in equal predictions across the sensitive features. In hate speech detection, however, equalizing model…
Large language models (LLMs) are increasingly popular but are also prone to generating bias, toxic or harmful language, which can have detrimental effects on individuals and communities. Although most efforts is put to assess and mitigate…
In this paper, we describe an approach to sentence categorization which has the originality to be based on natural properties of languages with no training set dependency. The implementation is fast, small, robust and textual errors…
To what extent can neural network models learn generalizations about language structure, and how do we find out what they have learned? We explore these questions by training neural models for a range of natural language processing tasks on…
Natural Language Inference is an important task for Natural Language Understanding. It is concerned with classifying the logical relation between two sentences. In this paper, we propose several text generative neural networks for…
Multilingual generative language models (LMs) are increasingly fluent in a large variety of languages. Trained on the concatenation of corpora in multiple languages, they enable powerful transfer from high-resource languages to low-resource…