ORPHEAS: A Cross-Lingual Greek-English Embedding Model for Retrieval-Augmented Generation

TL;DR

ORPHEAS is a specialized Greek-English embedding model designed to improve retrieval-augmented generation by capturing domain-specific and cross-lingual semantics, outperforming existing models.

Contribution

It introduces a high-quality, knowledge graph-based fine-tuning approach for Greek-English embeddings, enhancing cross-lingual retrieval in complex, domain-specific contexts.

Findings

ORPHEAS outperforms state-of-the-art multilingual models in retrieval benchmarks.

Fine-tuning on Greek with knowledge graphs maintains cross-lingual capabilities.

Domain-specific fine-tuning improves semantic representation for Greek.

Abstract

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.