Thibault Laugel
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Thibault Laugel has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
Marcin Detyniecki
Sorbonne Université, CNRS, LIP6
5 shared publications- Christophe Marsala
Sorbonne Université, CNRS, LIP6
4 shared publications - Marie-Jeanne Lesot
Sorbonne Université, CNRS, LIP6
4 shared publications - Adulam Jeyasothy
LIP6, Sorbonne Université, France
3 shared publications - Marcin Detyniecki
AXA AI Research, Paris, France
3 shared publications Vincent Grari
AXA Paris France
2 shared publications
Latest Publications
- 25 August 2026
- Published by Springer Nature
- p. 357-373
Alignment Reduces Expressed but Not Encoded Gender Bias: A Unified Framework and Study
- 25 August 2026
- Published by Springer Nature
- p. 357-373
Alignment Reduces Expressed but Not Encoded Gender Bias: A Unified Framework and Study
- 6 April 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Local post-hoc interpretability for black-box classifiers
Interprétabilité locale post-hoc des modèles de classification "boites noires": Cette thèse porte sur le domaine du XAI (explicabilité de l'IA), et plus particulièrement sur le paradigme de l'interprétabilité locale post-hoc, c'est-à-dire la génération d'explications pour une prédiction unique d'un classificateur entraîné. En particulier, nous étudions un contexte totalement agnostique, c'est-à-dire que l'explication est générée sans utiliser aucune connaissance sur le modèle de classification (traité comme une boîte noire) ni les données utilisées pour l'entraîner. Dans cette thèse, nous identifions plusieurs problèmes qui peuvent survenir dans ce contexte et qui peuvent être préjudiciables à l'interprétabilité. Nous nous proposons d'étudier chacune de ces questions et proposons des critères et des approches nouvelles pour les détecter et les caractériser. Les trois questions sur lesquelles nous nous concentrons sont : le risque de générer des explications qui sont hors distribution ; le risque de générer des explications qui ne peuvent être associées à aucune instance d'entraînement ; et le risque de générer des explications qui ne sont pas assez locales. Ces risques sont étudiés à travers deux catégories spécifiques d'approches de l'interprétabilité : les explications contrefactuelles et les modèles de substitution locaux.
- 6 April 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Local post-hoc interpretability for black-box classifiers
Interprétabilité locale post-hoc des modèles de classification "boites noires": Cette thèse porte sur le domaine du XAI (explicabilité de l'IA), et plus particulièrement sur le paradigme de l'interprétabilité locale post-hoc, c'est-à-dire la génération d'explications pour une prédiction unique d'un classificateur entraîné. En particulier, nous étudions un contexte totalement agnostique, c'est-à-dire que l'explication est générée sans utiliser aucune connaissance sur le modèle de classification (traité comme une boîte noire) ni les données utilisées pour l'entraîner. Dans cette thèse, nous identifions plusieurs problèmes qui peuvent survenir dans ce contexte et qui peuvent être préjudiciables à l'interprétabilité. Nous nous proposons d'étudier chacune de ces questions et proposons des critères et des approches nouvelles pour les détecter et les caractériser. Les trois questions sur lesquelles nous nous concentrons sont : le risque de générer des explications qui sont hors distribution ; le risque de générer des explications qui ne peuvent être associées à aucune instance d'entraînement ; et le risque de générer des explications qui ne sont pas assez locales. Ces risques sont étudiés à travers deux catégories spécifiques d'approches de l'interprétabilité : les explications contrefactuelles et les modèles de substitution locaux.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 15966-15978
SAKE: Steering Activations for Knowledge Editing
Marco Scialanga, Thibault Laugel, Vincent Grari, Marcin Detyniecki. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 15966-15978
Open AccessSAKE: Steering Activations for Knowledge Editing
Marco Scialanga, Thibault Laugel, Vincent Grari, Marcin Detyniecki. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- Open Access
Post-processing fairness with minimal changes
In this paper, we introduce a novel post-processing algorithm that is both model-agnostic and does not require the sensitive attribute at test time. In addition, our algorithm is explicitly designed to enforce minimal changes between biased and debiased predictions; a property that, while highly desirable, is rarely prioritized as an explicit objective in fairness literature. Our approach leverages a multiplicative factor applied to the logit value of probability scores produced by a black-box classifier. We demonstrate the efficacy of our method through empirical evaluations, comparing its performance against other four debiasing algorithms on two widely used datasets in fairness research.
Open AccessPost-processing fairness with minimal changes
In this paper, we introduce a novel post-processing algorithm that is both model-agnostic and does not require the sensitive attribute at test time. In addition, our algorithm is explicitly designed to enforce minimal changes between biased and debiased predictions; a property that, while highly desirable, is rarely prioritized as an explicit objective in fairness literature. Our approach leverages a multiplicative factor applied to the logit value of probability scores produced by a black-box classifier. We demonstrate the efficacy of our method through empirical evaluations, comparing its performance against other four debiasing algorithms on two widely used datasets in fairness research.
- 7 August 2024
- Published by Springer Nature in Machine Learning
- Vol. 113 (10) , 7997-8026
Understanding prediction discrepancies in classification
- 7 August 2024
- Published by Springer Nature in Machine Learning
- Vol. 113 (10) , 7997-8026
Understanding prediction discrepancies in classification
- Open Access
- 12 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 1859-1869
Achieving Diversity in Counterfactual Explanations: a Review and Discussion
- 12 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 1859-1869
Open AccessAchieving Diversity in Counterfactual Explanations: a Review and Discussion
- 4 July 2022
- Published by Springer Nature
- p. 707-719
Integrating Prior Knowledge in Post-hoc Explanations
- 4 July 2022
- Published by Springer Nature
- p. 707-719
Integrating Prior Knowledge in Post-hoc Explanations
- Open Access
Integrating Prior Knowledge in Post-hoc Explanations
In the field of eXplainable Artificial Intelligence (XAI), post-hoc interpretability methods aim at explaining to a user the predictions of a trained decision model. Integrating prior knowledge into such interpretability methods aims at improving the explanation understandability and allowing for personalised explanations adapted to each user. In this paper, we propose to define a cost function that explicitly integrates prior knowledge into the interpretability objectives: we present a general framework for the optimization problem of post-hoc interpretability methods, and show that user knowledge can thus be integrated to any method by adding a compatibility term in the cost function. We instantiate the proposed formalization in the case of counterfactual explanations and propose a new interpretability method called Knowledge Integration in Counterfactual Explanation (KICE) to optimize it. The paper performs an experimental study on several benchmark data sets to characterize the counterfactual instances generated by KICE, as compared to reference methods.
Open AccessIntegrating Prior Knowledge in Post-hoc Explanations
In the field of eXplainable Artificial Intelligence (XAI), post-hoc interpretability methods aim at explaining to a user the predictions of a trained decision model. Integrating prior knowledge into such interpretability methods aims at improving the explanation understandability and allowing for personalised explanations adapted to each user. In this paper, we propose to define a cost function that explicitly integrates prior knowledge into the interpretability objectives: we present a general framework for the optimization problem of post-hoc interpretability methods, and show that user knowledge can thus be integrated to any method by adding a compatibility term in the cost function. We instantiate the proposed formalization in the case of counterfactual explanations and propose a new interpretability method called Knowledge Integration in Counterfactual Explanation (KICE) to optimize it. The paper performs an experimental study on several benchmark data sets to characterize the counterfactual instances generated by KICE, as compared to reference methods.
- 1 January 2021
- Published by Springer Nature
- p. 521-533
How to Choose an Explainability Method? Towards a Methodical Implementation of XAI in Practice
- 1 January 2021
- Published by Springer Nature
- p. 521-533
How to Choose an Explainability Method? Towards a Methodical Implementation of XAI in Practice