Logo

Armel Randy Zebaze

I'm a final-year PhD student at Inria Paris in the ALMAnaCH team, working under the supervision of Rachel Bawden and Benoît Sagot on Machine Translation. My research focuses on improving the ability of LLMs to translate into low-resource languages.

I hold an Engineer's degree from Ecole Polytechnique and a M.S. degree from ENS Paris-Saclay (MVA).

When not doing research, I sleep.

Recent Articles

Disentangling Meaning from Language in LLM-based Machine Translation

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

Under reviewMachine TranslationMechanistic InterpretabilityArxivCode

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

AR Zebaze, Rachel Bawden, Benoît Sagot (2025)

Under reviewMachine TranslationCoTArXivCode

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

AR Zebaze, Benoît Sagot, Rachel Bawden (2025)

EMNLP 2025 FindingsMachine TranslationSynthetic Data GenerationArXivCode

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

AR Zebaze, Benoît Sagot, Rachel Bawden (2025)

EMNLP 2025 FindingsMachine TranslationCompositionalityArXivCode

Tree of Problems: Improving structured problem solving with compositionality

AR Zebaze, Benoît Sagot, Rachel Bawden (2024)

EMNLP 2024CoTCompositionalityArXivCode
See More Articles

Resume

PhD Student

Nov 2023 - Present

ALMAnaCH, Inria

Working on Machine Translation for low-resource languages.

ML Engineer intern

Apr 2023 - Sep 2023

Hugging Face

Worked on language models for code generation.

M.S CS - AI

Nov 2022 - Sep 2023

ENS Paris-Saclay

M2 MVA (Mathématiques, Vision, Apprentissage)

Research Assistant

Apr 2022 - Aug 2022

Oracle Labs

Worked on active learning for financial crime detection.

Engineer intern

Jun 2021 - Aug 2021

Alstom

Worked on a traffic management project.

Cycle ingénieur

Sep 2019 - Sep 2022

Ecole Polytechnique

Relevant Coursework: Database Management Systems, Data Analysis and Unsupervised Learning, Machine Learning and Deep Learning, Statistical Learning, Text Mining and NLP, Advanced Machine Learning and Autonomous Agents, Data Structures & Algorithms.