activity
20242026
collaborators
Showing cs.CLShow all

13 papers · 1 filter

cs.CL2026

OmnilingualGAIA2: Evaluating the Multilingual Gap in Frontier AI Agents

Andrea Caciolai, Pere-Lluís Huguet Cabot, Chierh Cheng +11

Agentic benchmarks aim to measure how well AI agents plan, search, execute, and recover within realistic multi-tool environments, but they are almost exclusively in English. As AI…

cs.CL2026

Omnilingual SONAR: Cross-Lingual and Cross-Modal Sentence Embeddings Bridging Massively Multilingual Text and Speech

Omnilingual SONAR Team, João Maria Janeiro, Pere-Lluís Huguet Cabot +17

Cross-lingual sentence encoders typically cover only a few hundred languages and often trade downstream quality for stronger alignment, limiting their adoption. We introduce OmniSO…

cs.CL2026

Omnilingual MT: Machine Translation for 1,600 Languages

Omnilingual MT Team, Belen Alastruey, Niyati Bafna +29

High-quality machine translation (MT) can scale to hundreds of languages, setting a high bar for multilingual systems. However, compared to the world's 7,000 languages, current sys…

cs.CL2025

Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages

Omnilingual ASR team, Gil Keren, Artyom Kozhevnikov +30

Automatic speech recognition (ASR) has advanced in high-resource languages, but most of the world's 7,000+ languages remain unsupported, leaving thousands of long-tail languages be…

cs.CL2025

LCFO: Long Context and Long Form Output Dataset and Benchmarking

Marta R. Costa-jussÃ, Pierre Andrews, Mariano Coria Meglioli +10

This paper presents the Long Context and Form Output (LCFO) benchmark, a novel evaluation framework for assessing gradual summarization and summary expansion capabilities across di…

cs.CL2025

BOUQuET: dataset, Benchmark and Open initiative for Universal Quality Evaluation in Translation

The Omnilingual MT Team, Pierre Andrews, Mikel Artetxe +14

BOUQuET is a multi-way, multicentric and multi-register/domain dataset and benchmark, and a broader collaborative initiative. This dataset is handcrafted in 8 non-English languages…