6 papers
Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs
Sara Papi, Javier Garcia Gilabert, Zachary Hopton +8
As Large Language Models (LLMs) expand beyond text, integrating speech as a native modality has given rise to SpeechLLMs, which directly process spoken language and enable speech-t…
Gender Bias in MT for a Genderless Language: New Benchmarks for Basque
Amaia Murillo, Olatz-Perez-de-Viñaspre, Naiara Perez
Large language models (LLMs) and machine translation (MT) systems are increasingly used in our daily lives, but their outputs can reproduce gender bias present in the training data…
ACADATA: Parallel Dataset of Academic Data for Machine Translation
Iñaki Lacunza, Javier Garcia Gilabert, Francesca De Luca Fornaciari +4
We present ACADATA, a high-quality parallel dataset for academic translation, that consists of two subsets: ACAD-TRAIN, which contains approximately 1.5 million author-generated pa…
From SALAMANDRA to SALAMANDRATA: BSC Submission for WMT25 General Machine Translation Shared Task
Javier Garcia Gilabert, Xixian Liao, Severino Da Dalt +8
In this paper, we present the SALAMANDRATA family of models, an improved iteration of SALAMANDRA LLMs (Gonzalez-Agirre et al., 2025) specifically trained to achieve strong performa…
MT-LENS: An all-in-one Toolkit for Better Machine Translation Evaluation
Javier GarcÃa Gilabert, Carlos Escolano, Audrey Mash +2
We introduce MT-LENS, a framework designed to evaluate Machine Translation (MT) systems across a variety of tasks, including translation quality, gender bias detection, added toxic…
Investigating the translation capabilities of Large Language Models trained on parallel data only
Javier GarcÃa Gilabert, Carlos Escolano, Aleix Sant Savall +4
In recent years, Large Language Models (LLMs) have demonstrated exceptional proficiency across a broad spectrum of Natural Language Processing (NLP) tasks, including Machine Transl…