Publications

Thibaud Leteno, Antoine Gourru, Charlotte Laclau, Christophe Gravier (2026). Equitable Alignment of LLMs Across Languages with Regularized Direct Preference Optimization. EMNLP 2026.

PDF Cite Code DOI

Irina Proskurina, Guillaume Metzler, Antoine Gourru, Julien Velcin (2026). Debias-SparseGPT: Bias-Aware Pruning for Large Language Models. EMNLP 2026.

PDF Cite Code DOI

Irina Proskurina, Guillaume Metzler, Julien Velcin (2026). Fair-GPTQ: Bias-Aware Quantization for Large Language Models. TACL.

Irina Proskurina (2026). Open Diké Leaderboard. Software.

Cite Code Project

Irina Proskurina, Marc-Antoine Carpentier, Julien Velcin (2026). HatePrototypes: Interpretable and Transferable Representations for Implicit and Explicit Hate Speech Detection. LREC 2026.

PDF Cite Code DOI

Irina Proskurina (2026). Towards an Unbiased Compression of Large Language Models. PhD Thesis.

Thibaud Leteno (2025). Contributions to Fairness-aware and Aligned Large Language Models. PhD Thesis.

Anthony Dubreuil, Antoine Gourru, Christine Largeron, Amine Trabelsi (2025). Are Stereotypes Leading LLMs’ Zero-Shot Stance Detection ?. EMNLP 2025.

PDF Cite Code DOI

Thibaud Leteno, Irina Proskurina, Antoine Gourru, Julien Velcin, Charlotte Laclau, Guillaume Metzler, Christophe Gravier (2025). HistoiresMorales: A French Dataset for Assessing Moral Alignment. NAACL 2025.

PDF Cite Code Source Document DOI

Thibaud Leteno, Michael Perrot, Charlotte Laclau, Antoine Gourru, Christophe Gravier (2025). Fair Text Classification via Transferable Representations. Journal of Machine Learning Research.

PDF Cite Code DOI

Irina Proskurina, Luc Brun, Guillaume Metzler, Julien Velcin (2024). When Quantization Affects Confidence of Large Language Models?. Findings of the Association for Computational Linguistics: NAACL 2024.

PDF Cite Code Slides DOI

Caroline Brun, Vassilina Nikoulina (2024). FrenchToxicityPrompts: a Large Benchmark for Evaluating and Mitigating Toxicity in French Texts. Proceedings of TRAC workshop @ LREC-COLING-2024.

PDF Cite Code Slides DOI

Thomas Palmeira Ferraz, Marcely Zanon Boito, Caroline Brun, Vassilina Nikoulina (2024). Multilingual Distilwhisper: Efficient Distillation of Multi-Task Speech Models Via Language-Specific Experts. ICASSP 2024.

PDF Cite Code DOI

Thibaud Leteno, Antoine Gourru, Charlotte Laclau, Rémi Emonet, Christophe Gravier (2023). Fair Text Classification with Wasserstein Independence. Proceedings of EMNLP.

PDF Cite Code DOI

Irina Proskurina, Guillaume Metzler, Julien Velcin (2023). Mini Minds: Exploring Bebeshka and Zlata Baby Models. Proceedings of CoNLL.

PDF Cite Code DOI

Irina Proskurina, Guillaume Metzler, Julien Velcin (2023). The Other Side of Compression: Measuring Bias in Pruned Transformers. Proceedings of IDA.

PDF Cite Code DOI

Thibaud Leteno, Antoine Gourru, Charlotte Laclau, Christophe Gravier (2023). An Investigation of Structures Responsible for Gender Bias in BERT and DistilBERT. Proceedings of IDA.

PDF Cite Code DOI

Alireza Mohammadshahi, Vassilina Nikoulina, Caroline Brun (2022). What Do Compressed Multilingual Machine Translation Models Forget?. Findings of EMNLP.

PDF Cite Code DOI

Alireza Mohammadshahi, Vassilina Nikoulina, Caroline Brun (2022). SMaLL-100: Introducing Shallow Multilingual Machine Translation Model for Low-Resource Languages. Proceedings of EMNLP.

PDF Cite Code DOI