José Pombal | Sword Health

About Me

I am a Senior Research Scientist at Sword Health, and a PhD student at Instituto Superior Técnico and Instituto de Telecomunicações in Lisbon, advised by Prof. André Martins and Ricardo Rei. I’m currently working on building frontier LLMs for healthcare with a focus on applications for mental health, and I’m particularly interested in the automatic evaluation of such models. Previously, I worked on the development and evaluation of multilingual LLMs at Unbabel, and fairness-aware ML for fraud detection at Feedzai.

News

[July 2025] Joined Sword Health as a Senior Research Scientist.
[June 2025] Released Tower+, the first suite of translation-specialized LLMs that are also SotA in general capabilities.
[May 2025] Two papers accepted at COLM 2025: M-Prometheus and Zero-shot Benchmarking, both about general-purpose automatic evaluation of language models, the latter with a sprinkle of multimodality.
[April 2025] Two papers accepted at TACL on context-aware translation (presented at ACL 2025) and metric interference.
[January 2025] Co-developed and released EuroLLM 2B and 9B.
[October 2024] Spotlight presentation of Tower at COLM 2024.
[August 2024] Won the WMT24 General MT and Biomedical shared tasks with Tower v2. Won the Chat MT shared task with TowerChat.
[January 2024] First release of Tower, a SotA open multilingual LLM for translation-related tasks.
[March 2023] Joined Unbabel as a Research Scientist.

Selected Publications

* = equal contribution

Zero-shot Benchmarking: A Framework for Flexible and Scalable Automatic Evaluation of Language Models

José Pombal, Nuno M. Guerreiro, Ricardo Rei, André F. T. Martins

Conference on Language Modeling (COLM), 2025.

Paper Code
Tower+: Bridging Generality and Translation Specialization in Multilingual LLMs

Ricardo Rei*, Nuno M. Guerreiro, José Pombal*, João Alves*, Pedro Teixeirinha, Amin Farajian, André F. T. Martins

arXiv preprint (2025)

Paper Models and data
M-Prometheus: A Suite of Open Multilingual LLM Judges

José Pombal, Dongkeun Yoon, Patrick Fernandes, Ian Wu, Seungone Kim, Ricardo Rei, André F. T. Martins

Conference on Language Modeling (COLM), 2025.

Paper Models and data
Adding Chocolate to Mint: Mitigating Metric Interference in Machine Translation

José Pombal, Nuno M. Guerreiro, Ricardo Rei, André F. T. Martins

Transactions of the Association for Computacional Linguistics (TACL), 2025.

Paper
A Context-aware Framework for Translation-mediated Conversations

José Pombal*, Sweta Agrawal*, Emmanouil Zaranis, Patrick Fernandes, André F. T. Martins

Transactions of the Association for Computacional Linguistics (TACL), 2025. Presented at ACL 2025.

Paper
Tower: An Open Multilingual Large Language Model for Translation-Related Tasks

Duarte M. Alves*, José Pombal*, Nuno M. Guerreiro*, Pedro H. Martins, João Alves, Amin Farajian, Ben Peters, Ricardo Rei, Patrick Fernandes, Sweta Agrawal, Pierre Colombo, José G.C. de Souza, André F. T. Martins

Conference on Language Modeling (COLM), 2024. (Spotlight)

Paper Models and data Evaluation code Zeno project