151 citations · 170 across the 15 of their papers we have counts for
10 papers · 1 filter
Debias-SparseGPT: Bias-Aware Pruning for Large Language Models
Irina Proskurina, Guillaume Metzler, Antoine Gourru +1
Model compression techniques such as pruning and quantization facilitate the efficient deployment and acceleration of Large Language Models (LLMs). However, recent studies show tha…
The Fairness Collapse Phenomenon: Bias Amplification in Language Models Trained on Synthetic Data
Irina Proskurina, Antoine Gourru, Julien Velcin
Generative models trained on artificially generated data have been shown to exhibit model collapse, resulting in significant performance degradation. As synthetic content increasin…
Beyond Arrow's Impossibility: Fairness as an Emergent Property of Multi-Agent Collaboration
Sayan Kumar Chaki, Antoine Gourru, Julien Velcin
Fairness in language models is typically studied as a property of a single, centrally optimized model. As large language models become increasingly agentic, we propose that fairnes…
Are Stereotypes Leading LLMs' Zero-Shot Stance Detection ?
Anthony Dubreuil, Antoine Gourru, Christine Largeron +1
Large Language Models inherit stereotypes from their pretraining data, leading to biased behavior toward certain social groups in many Natural Language Processing tasks, such as ha…
Histoires Morales: A French Dataset for Assessing Moral Alignment
Thibaud Leteno, Irina Proskurina, Antoine Gourru +4
Aligning language models with human values is crucial, especially as they become more integrated into everyday life. While models are often adapted to user preferences, it is equal…
Capturing Style in Author and Document Representation
Enzo Terreau, Antoine Gourru, Julien Velcin
A wide range of Deep Natural Language Processing (NLP) models integrates continuous and low dimensional representations of words and documents. Surprisingly, very few models study…
Fine-tuning Strategies for Domain Specific Question Answering under Low Annotation Budget Constraints
Kunpeng Guo, Dennis Diefenbach, Antoine Gourru +1
The progress introduced by pre-trained language models and their fine-tuning has resulted in significant improvements in most downstream NLP tasks. The unsupervised training of a l…
Wikidata as a seed for Web Extraction
Kunpeng Guo, Dennis Diefenbach, Antoine Gourru +1
Wikidata has grown to a knowledge graph with an impressive size. To date, it contains more than 17 billion triples collecting information about people, places, films, stars, public…
An investigation of structures responsible for gender bias in BERT and DistilBERT
Thibaud Leteno, Antoine Gourru, Charlotte Laclau +1
In recent years, large Transformer-based Pre-trained Language Models (PLM) have changed the Natural Language Processing (NLP) landscape, by pushing the performance boundaries of th…
Fair Text Classification with Wasserstein Independence
Thibaud Leteno, Antoine Gourru, Charlotte Laclau +2
Group fairness is a central research topic in text classification, where reaching fair treatment between sensitive groups (e.g. women vs. men) remains an open challenge. This paper…