Dolamic, Ljiljana

4 publications

TMLR 2026 Implicit Probabilistic Reasoning Does Not Reflect Explicit Answers in Large Language Models Manuel Mondal, Ljiljana Dolamic, Gérôme Bovet, Philippe Cudre-Mauroux, Julien Audiffren

NeurIPSW 2024 NMT-Obfuscator Attack: Ignore a Sentence in Translation with Only One Word Sahar Sadrizadeh, César Descalzo, Ljiljana Dolamic, Pascal Frossard

TMLR 2023 TransFool: An Adversarial Attack Against Neural Machine Translation Models Sahar Sadrizadeh, Ljiljana Dolamic, Pascal Frossard

AAAI 2021 MARTA: Leveraging Human Rationales for Explainable Text Classification Ines Arous, Ljiljana Dolamic, Jie Yang, Akansha Bhardwaj, Giuseppe Cuccu, Philippe Cudré-Mauroux