Armel Randy Zebaze

Home Publications Resume

All Articles

Disentangling Meaning from Language in LLM-based Machine Translation

Théo Lasnier $^*$ , AR Zebaze $^*$ , Djamé Seddah, Rachel Bawden, Benoît Sagot (2026)

Under reviewMachine TranslationMechanistic InterpretabilityArxiv Code

LLM Reasoning for Machine Translation: Synthetic Data Generation over Thinking Tokens

AR Zebaze, Rachel Bawden, Benoît Sagot (2025)

Under reviewMachine TranslationCoTArXiv Code

TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation

AR Zebaze, Benoît Sagot, Rachel Bawden (2025)

EMNLP 2025 FindingsMachine TranslationSynthetic Data GenerationArXiv Code

Compositional Translation: A Novel LLM-based Approach for Low-resource Machine Translation

AR Zebaze, Benoît Sagot, Rachel Bawden (2025)

EMNLP 2025 FindingsMachine TranslationCompositionalityArXiv Code

Tree of Problems: Improving structured problem solving with compositionality

AR Zebaze, Benoît Sagot, Rachel Bawden (2024)

EMNLP 2024CoTCompositionalityArXiv Code

In-Context Example Selection via Similarity Search Improves Low-Resource Machine Translation

AR Zebaze, Benoît Sagot, Rachel Bawden (2024)

NAACL 2025 FindingsMachine TranslationIn-Context LearningArXiv Code