Thibault Laugel

37 papers A* 2Journal 24Unranked 10

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Alignment Reduces Expressed but Not Encoded Gender Bias: A Unified Framework and Study. CoRR Nour Bouchouchi, Thibault Laugel, Xavier Renard, Christophe Marsala, Marie-Jeanne Lesot, Marcin Detyniecki
2025	J	`jnl`	ACT: Agentic Classification Tree. CoRR Vincent Grari, Tim Arni, Thibault Laugel, Sylvain Lamprier, James Zou, Marcin Detyniecki
2025	J	`jnl`	Controlled Model Debiasing through Minimal and Interpretable Updates. CoRR Federico Di Gennaro, Thibault Laugel, Vincent Grari, Marcin Detyniecki
2025	J	`jnl`	Controlled Model Debiasing through Minimal and Interpretable Updates. Trans. Mach. Learn. Res. Federico Di Gennaro, Thibault Laugel, Vincent Grari, Marcin Detyniecki
2025	J	`jnl`	Metric assessment protocol in the context of answer fluctuation on MCQ tasks. CoRR Ekaterina Goliakova, Xavier Renard, Marie-Jeanne Lesot, Thibault Laugel, Christophe Marsala, Marcin Detyniecki
2025	—	`conf`	SAKE: Steering Activations for Knowledge Editing. ACL (1) Marco Scialanga, Thibault Laugel, Vincent Grari, Marcin Detyniecki
2025	J	`jnl`	SAKE: Steering Activations for Knowledge Editing. CoRR Marco Scialanga, Thibault Laugel, Vincent Grari, Marcin Detyniecki
2025	—	`conf`	When Mitigating Bias is Unfair: Multiplicity and Arbitrariness in Algorithmic Group Fairness. SaTML Natasa Krco, Thibault Laugel, Vincent Grari, Jean-Michel Loubes, Marcin Detyniecki
2024	A*	`conf`	On the Fairness ROAD: Robust Optimization for Adversarial Debiasing. ICLR Vincent Grari, Thibault Laugel, Tatsunori Hashimoto, Sylvain Lamprier, Marcin Detyniecki
2024	J	`jnl`	Post-processing fairness with minimal changes. CoRR Federico Di Gennaro, Thibault Laugel, Vincent Grari, Xavier Renard, Marcin Detyniecki
2024	J	`jnl`	Understanding prediction discrepancies in classification. Mach. Learn. Xavier Renard, Thibault Laugel, Marcin Detyniecki
2024	J	`jnl`	Why do explanations fail? A typology and discussion on failures in XAI. CoRR Clara Bove, Thibault Laugel, Marie-Jeanne Lesot, Charles Tijus, Marcin Detyniecki
2023	J	`jnl`	A general framework for personalising post hoc explanations through user knowledge integration. Int. J. Approx. Reason. Adulam Jeyasothy, Thibault Laugel, Marie-Jeanne Lesot, Christophe Marsala, Marcin Detyniecki
2023	—	`conf`	Achieving Diversity in Counterfactual Explanations: a Review and Discussion. FAccT Thibault Laugel, Adulam Jeyasothy, Marie-Jeanne Lesot, Christophe Marsala, Marcin Detyniecki
2023	J	`jnl`	Achieving Diversity in Counterfactual Explanations: a Review and Discussion. CoRR Thibault Laugel, Adulam Jeyasothy, Marie-Jeanne Lesot, Christophe Marsala, Marcin Detyniecki
2023	—	`conf`	Knowledge Integration in XAI with Gödel Integrals. FUZZ Adulam Jeyasothy, Agnès Rico, Marie-Jeanne Lesot, Christophe Marsala, Thibault Laugel
2023	J	`jnl`	On the Fairness ROAD: Robust Optimization for Adversarial Debiasing. CoRR Vincent Grari, Thibault Laugel, Tatsunori Hashimoto, Sylvain Lamprier, Marcin Detyniecki
2023	J	`jnl`	When Mitigating Bias is Unfair: A Comprehensive Study on the Impact of Bias Mitigation Algorithms. CoRR Natasa Krco, Thibault Laugel, Jean-Michel Loubes, Marcin Detyniecki
2022	—	`conf`	Integrating Prior Knowledge in Post-hoc Explanations. IPMU (2) Adulam Jeyasothy, Thibault Laugel, Marie-Jeanne Lesot, Christophe Marsala, Marcin Detyniecki
2022	J	`jnl`	Integrating Prior Knowledge in Post-hoc Explanations. CoRR Adulam Jeyasothy, Thibault Laugel, Marie-Jeanne Lesot, Christophe Marsala, Marcin Detyniecki
2022	—	`conf`	Intégration de connaissances dans les méthodes d'explications post-hoc. LFA Adulam Jeyasothy, Thibault Laugel, Marie-Jeanne Lesot, Christophe Marsala, Marcin Detyniecki
2021	—	`conf`	How to Choose an Explainability Method? Towards a Methodical Implementation of XAI in Practice. PKDD/ECML Workshops (1) Tom Vermeire, Thibault Laugel, Xavier Renard, David Martens, Marcin Detyniecki
2021	J	`jnl`	How to choose an Explainability Method? Towards a Methodical Implementation of XAI in Practice. CoRR Tom Vermeire, Thibault Laugel, Xavier Renard, David Martens, Marcin Detyniecki
2021	J	`jnl`	On the overlooked issue of defining explanation objectives for local-surrogate explainers. CoRR Rafael Poyiadzi, Xavier Renard, Thibault Laugel, Raúl Santos-Rodríguez, Marcin Detyniecki
2021	J	`jnl`	Understanding Prediction Discrepancies in Machine Learning Classifiers. CoRR Xavier Renard, Thibault Laugel, Marcin Detyniecki
2021	J	`jnl`	Understanding surrogate explanations: the interplay between complexity, fidelity and coverage. CoRR Rafael Poyiadzi, Xavier Renard, Thibault Laugel, Raúl Santos-Rodríguez, Marcin Detyniecki
2020	—	`—`	Local Post-hoc Interpretability for Black-box Classifiers. (Interprétabilité Locale Post-hoc des Algorithmes de Classification "Boîtes noires"). Thibault Laugel
2019	J	`jnl`	Imperceptible Adversarial Attacks on Tabular Data. CoRR Vincent Ballet, Xavier Renard, Jonathan Aigrain, Thibault Laugel, Pascal Frossard, Marcin Detyniecki
2019	J	`jnl`	Issues with post-hoc counterfactual explanations: a discussion. CoRR Thibault Laugel, Marie-Jeanne Lesot, Christophe Marsala, Marcin Detyniecki
2019	A*	`conf`	The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations. IJCAI Thibault Laugel, Marie-Jeanne Lesot, Christophe Marsala, Xavier Renard, Marcin Detyniecki
2019	J	`jnl`	The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations. CoRR Thibault Laugel, Marie-Jeanne Lesot, Christophe Marsala, Xavier Renard, Marcin Detyniecki
2019	—	`conf`	Unjustified Classification Regions and Counterfactual Explanations in Machine Learning. ECML/PKDD (2) Thibault Laugel, Marie-Jeanne Lesot, Christophe Marsala, Xavier Renard, Marcin Detyniecki
2018	—	`conf`	Comparison-Based Inverse Classification for Interpretability in Machine Learning. IPMU (1) Thibault Laugel, Marie-Jeanne Lesot, Christophe Marsala, Xavier Renard, Marcin Detyniecki
2018	J	`jnl`	Defining Locality for Surrogates in Post-hoc Interpretablity. CoRR Thibault Laugel, Xavier Renard, Marie-Jeanne Lesot, Christophe Marsala, Marcin Detyniecki
2018	—	`conf`	Detecting Potential Local Adversarial Examples for Human-Interpretable Defense. Nemesis/UrbReas/SoGood/IWAISe/GDM@PKDD/ECML Xavier Renard, Thibault Laugel, Marie-Jeanne Lesot, Christophe Marsala, Marcin Detyniecki
2018	J	`jnl`	Detecting Potential Local Adversarial Examples for Human-Interpretable Defense. CoRR Xavier Renard, Thibault Laugel, Marie-Jeanne Lesot, Christophe Marsala, Marcin Detyniecki
2017	J	`jnl`	Inverse Classification for Comparison-based Interpretability in Machine Learning. CoRR Thibault Laugel, Marie-Jeanne Lesot, Christophe Marsala, Xavier Renard, Marcin Detyniecki