Papers
arxiv:2608.01389

KoVRE: Training an Efficient Embedding Model for Korean Visual Document Retrieval

Published on Aug 2
Authors:
,
,

Abstract

A 2B-parameter Korean visual document retriever using single-vector embeddings and targeted bilingual training outperforms larger and multi-vector baselines.

Visual Document Retrieval (VDR) directly matches text queries against document images, preserving visual and structural information that may be lost during text extraction. However, existing VDR models and training resources remain predominantly English-centric, while many high-performing systems rely on massive backbones or storage-intensive multi-vector representations. To address these limitations, we introduce KoVRE: Korean Visual Document Retrieval Embedding, a single-vector retriever for Korean visual documents, alongside a comprehensive training recipe. We train the model on 708,729 Korean and English query-page pairs using positive-aware hard-negative mining and conduct controlled analyses of training-data composition, hard-negative treatment, and reranker-based knowledge distillation. Across Korean visual document retrieval benchmarks, our 2B model substantially improves over the base backbone model, outperforming both its 8B single-vector counterpart and a strong multi-vector baseline. These results demonstrate that targeted bilingual supervision and our carefully designed training strategies can produce a highly effective Korean VDR model across diverse document domains, without requiring a scaled-up backbone or multi-vector representations.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2608.01389
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 2

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2608.01389 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2608.01389 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.