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

Ioannis E. Livieris, Athanasios Koursaris, Alexandra Apostolopoulou, Konstantinos Kanaris Dimitris Tsakalidis, George Domalis
4/22/2026
cs.CLcs.AI

No official code found. Best implementation: Arxiv-to-code/arxiv-260420666-orpheas-a-cross-lingual-greek-english-embedding-model-for-re (0 stars, last commit 2026-04-23).

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.

View on arXivView PDF

Code Implementations(1)

Arxiv-to-code/arxiv-260420666-orpheas-a-cross-lingual-greek-english-embedding-model-for-reCommunity69%

Implementation of ORPHEAS: A Cross-Lingual Greek-English Embedding Model for Retrieval-Augmented Generation (arXiv:2604.20666) https://arxiv.org/abs/2604.20666

00PythonApr 23, 20266 months ago

Similar Papers

Robust Cross-lingual Embeddings from Parallel Sentences

84% match1 repo222019

Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrieval

84% match1 repo502023

Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models

84% match2025

Improving Cross-lingual Information Retrieval on Low-Resource Languages via Optimal Transport Distillation

83% match2023

Inspicio: Open-Vocabulary, LLM-Based Sense Retrieval for Historical Languages

83% match2026

Towards Better Monolingual Japanese Retrievers with Multi-Vector Models

83% match2023

Cite this paper

@article{livieris2026orpheas,
  title  = {ORPHEAS: A Cross-Lingual Greek-English Embedding Model for Retrieval-Augmented Generation},
  author = {Ioannis E. Livieris and Athanasios Koursaris and Alexandra Apostolopoulou and Konstantinos Kanaris Dimitris Tsakalidis and George Domalis},
  year   = {2026},
  eprint = {2604.20666},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2604.20666v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2604.20666.svg)](https://codeofpaper.com/paper/2604.20666)

Discussion