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

2026-04-22

AI Summary

This work addresses the suboptimal performance of existing general-purpose multilingual embedding models on Greek–English retrieval-augmented generation tasks, which struggle to simultaneously capture the morphological complexity of Greek and the structural nuances of domain-specific terminology. To overcome this limitation, the authors propose a bilingual embedding model specifically tailored for the Greek–English language pair. The approach leverages knowledge graph–guided construction of high-quality fine-tuning data and employs domain-adaptive training across diverse corpora. This strategy enhances the semantic representation quality of Greek while preserving strong cross-lingual alignment capabilities. Experimental results demonstrate that the proposed model consistently outperforms state-of-the-art multilingual embedding baselines on both monolingual and cross-lingual retrieval benchmarks.

Technology Category

• Natural Language Processing: Lexical Semantics and Morphology
• Machine Learning: Large Multimodal Models (LMMs)
• Knowledge Representation and Reasoning: Knowledge Representation Languages

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• cross-lingual embedding
• Greek-English retrieval
• morphological complexity
• domain-specific semantics
• retrieval-augmented generation

Innovation

• cross-lingual embedding
• retrieval-augmented generation
• Greek-English bilingual model
• knowledge graph-based fine-tuning
• morphologically complex languages