Large-scale deployment of large language models (LLMs) in various applications, such as
chatbots and virtual assistants, requires LLMs to be culturally sensitive to the user to ensure …

This paper presents BookNLP-fr: the adaptation to French of BookNLP, an existing NLP
pipeline tailored for literary texts in English. We provide an overview of the challenges …

AI-based systems such as language models can replicate and amplify social biases
reflected in their training data. Among other questionable behavior, this can lead to LM …

The advancements of Large Language Models (LLMs) have decentralized the responsibility
for the transparency of AI usage. Specifically, LLM users are now encouraged or required to …

Gender bias has been extensively studied in both the educational field and the Natural
Language Processing (NLP) field, the former using human coding to identify patterns …

Constructing a timeline requires identifying the chronological order of events in an article. In
prior timeline construction datasets, temporal orders are typically annotated by either event …

Recent studies show that traditional fairytales are rife with harmful gender biases. To help
mitigate these gender biases in fairytales, this work aims to assess learned biases of …

We introduce CLAUSE-ATLAS, a resource of XIX and XX century English novels annotated
automatically. This corpus, which contains 41,715 labeled clauses, allows to study stories as …

Con el frenético avance de la inteligencia artificial (IA), se ponen de manifiesto las múltiples
funcionalidades que esta puede tener en distintos sectores, incluida la producción de …

Linguistic expressions betray biases even if their producers are not cognizant of them. Let
alone malicious actors, even benign or ordinary people may be perpetuating biased …