ORPHEAS: A Cross-Lingual Greek-English Embedding Model for Retrieval-Augmented Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914499155460096 |
|---|---|
| author | Livieris, Ioannis E. Koursaris, Athanasios Apostolopoulou, Alexandra Tsakalidis, Konstantinos Kanaris Dimitris Domalis, George |
| author_facet | Livieris, Ioannis E. Koursaris, Athanasios Apostolopoulou, Alexandra Tsakalidis, Konstantinos Kanaris Dimitris Domalis, George |
| contents | Effective retrieval-augmented generation across bilingual Greek--English applications requires embedding models capable of capturing both domain-specific semantic relationships and cross-lingual semantic alignment. Existing multilingual embedding models distribute their representational capacity across numerous languages, limiting their optimization for Greek and failing to encode the morphological complexity and domain-specific terminological structures inherent in Greek text. In this work, we propose ORPHEAS, a specialized Greek--English embedding model for bilingual retrieval-augmented generation. ORPHEAS is trained with a high quality dataset generated by a knowledge graph-based fine-tuning methodology which is applied to a diverse multi-domain corpus, which enables language-agnostic semantic representations. The numerical experiments across monolingual and cross-lingual retrieval benchmarks reveal that ORPHEAS outperforms state-of-the-art multilingual embedding models, demonstrating that domain-specialized fine-tuning on morphologically complex languages does not compromise cross-lingual retrieval capability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_20666 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ORPHEAS: A Cross-Lingual Greek-English Embedding Model for Retrieval-Augmented Generation Livieris, Ioannis E. Koursaris, Athanasios Apostolopoulou, Alexandra Tsakalidis, Konstantinos Kanaris Dimitris Domalis, George Computation and Language Artificial Intelligence 68T50, 68T01, 68P20, 68T05, 68T30 H.3.3; I.2.7; I.2.6; H.3.1; I.2.10 Effective retrieval-augmented generation across bilingual Greek--English applications requires embedding models capable of capturing both domain-specific semantic relationships and cross-lingual semantic alignment. Existing multilingual embedding models distribute their representational capacity across numerous languages, limiting their optimization for Greek and failing to encode the morphological complexity and domain-specific terminological structures inherent in Greek text. In this work, we propose ORPHEAS, a specialized Greek--English embedding model for bilingual retrieval-augmented generation. ORPHEAS is trained with a high quality dataset generated by a knowledge graph-based fine-tuning methodology which is applied to a diverse multi-domain corpus, which enables language-agnostic semantic representations. The numerical experiments across monolingual and cross-lingual retrieval benchmarks reveal that ORPHEAS outperforms state-of-the-art multilingual embedding models, demonstrating that domain-specialized fine-tuning on morphologically complex languages does not compromise cross-lingual retrieval capability. |
| title | ORPHEAS: A Cross-Lingual Greek-English Embedding Model for Retrieval-Augmented Generation |
| topic | Computation and Language Artificial Intelligence 68T50, 68T01, 68P20, 68T05, 68T30 H.3.3; I.2.7; I.2.6; H.3.1; I.2.10 |
| url | https://arxiv.org/abs/2604.20666 |