6 papers
Influcoder: Distilling Decoders' Gradient Influence Rankings into an Encoder for Data Attribution
Dimitri Kachler, Damien Sileo, Pascal Denis
With the growth of LLMs' (Large Language Models) capabilities, there has been an increasing push to curate high quality datasets by filtering samples in the training data. In gener…
Synthetic Data Generation for Intersectional Fairness by Leveraging Hierarchical Group Structure
Gaurav Maheshwari, Aurélien Bellet, Pascal Denis +1
In this paper, we introduce a data augmentation approach specifically tailored to enhance intersectional fairness in classification tasks. Our method capitalizes on the hierarchica…
A Tale of Two Laws of Semantic Change: Predicting Synonym Changes with Distributional Semantic Models
Bastien Liétard, Mikaela Keller, Pascal Denis
Lexical Semantic Change is the study of how the meaning of words evolves through time. Another related question is whether and how lexical relations over pairs of words, such as sy…
Fair Without Leveling Down: A New Intersectional Fairness Definition
Gaurav Maheshwari, Aurélien Bellet, Pascal Denis +1
In this work, we consider the problem of intersectional group fairness in the classification setting, where the objective is to learn discrimination-free models in the presence of…
Exploring Category Structure with Contextual Language Models and Lexical Semantic Networks
Joseph Renner, Pascal Denis, Rémi Gilleron +1
Recent work on predicting category structure with distributional models, using either static word embeddings (Heyman and Heyman, 2019) or contextualized language models (CLMs) (Mis…
Fair NLP Models with Differentially Private Text Encoders
Gaurav Maheshwari, Pascal Denis, Mikaela Keller +1
Encoded text representations often capture sensitive attributes about individuals (e.g., race or gender), which raise privacy concerns and can make downstream models unfair to cert…