跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 10 天前AI 評分45

EvenVLM:用於瀕危 Even 語言的文本與多模態數據集及視覺語言微調

EvenVLM: A Text and Multimodal Dataset for the Even Language with Vision-Language Fine-Tuning

AI 導讀

EvenVLM 提供首個面向瀕危 Even 語言的文本與多模態 VQA 數據集,並以 Qwen3-VL-4B 的 LoRA 微調提升文本任務、翻譯和 VQA 表現。

正文

Published on Nov 12

·

Submitted by

Daniil

on Nov 16

Authors:

Abstract

EvenVLM provides a text and multimodal VQA dataset for the endangered Even language, with tokenizer expansion and LoRA fine-tuning improving translation, text benchmarks, and VQA accuracy.

We present EvenVLM, the first text and multimodal (VQA) dataset for Even (Lamut), an endangered Northern Tungusic language spoken by approximately 6,800 people in Siberia. Our dataset comprises 50,521 structured Even-Russian entries extracted from dictionary and phrasebook sources via GPT-4o Mini-based parsing, from which we synthetically generate 107,543 training examples spanning translation, grammar, reading comprehension, and semantic classification. To address tokenization inefficiency on Even's agglutinative morphology, we propose a three-step tokenizer expansion algorithm that adds Even-specific graphemes (eng, oe, o-umlaut), whitelisted vocabulary, and BPE merges, reducing average tokens per word by 27% (4.99 to 3.64). Using LoRA fine-tuning of Qwen3-VL-4B, we adapt the model for text tasks (0.53% trainable parameters, rank 32) and separately for visual question answering (rank 64, frozen vision encoder). Our best configuration achieves 11.4% exact match and a 13.6 weighted score on text benchmarks, 0.1283 chrF for sentence translation, and 65% accuracy on VQA (up from 0% for the base model and text-only fine-tuning). We release our datasets, evaluation benchmarks, and training pipeline to support further research on Even and other low-resource languages.

View arXiv page View PDF Project page Add to collection

Get this paper in your agent:

hf papers read 2611.16500

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.16500 in a model README.md to link it from this page.

Datasets citing this paper 1

DaniilMako/even-russian-corpus

Viewer •

Updated about 5 hours ago

•

50.5k

•

111

•

1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.16500 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.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co