“Krikri: Advancing Open Large Language Models for Greek” was published in Findings of EMNLP 2025 and presents Llama-Krikri-8B, an open large language model tailored for Greek.
The work is important for the group’s broader language and content technologies profile: it supports Modern Greek, English, polytonic text and Ancient Greek, and includes public benchmarks for evaluating Greek-language understanding, generation and code-related capabilities.
- MediaLab-linked authors: Georgios Paraskevopoulos, Athanasios Katsamanis, Vassilis Katsouros
- Venue: Findings of the Association for Computational Linguistics: EMNLP 2025
- Publication month: November 2025
- DOI: 10.18653/v1/2025.findings-emnlp.268
- ACL Anthology: paper record
You may also like
-
TMLR 2026: prescriptive SVD-inspired attention via spectral energy retention
-
Towards Heritage World Models: from digital twins to predictive heritage systems
-
ICASSP 2026: representation-diverse self-supervision for bioacoustic learning
-
AISTATS 2026: process-tensor tomography of SGD and training memory
-
ICPRAM 2026: two-stage angular alignment for positive-unlabeled learning