用大模型提升盲文翻译准确率，解决数据少、混合文本难处理问题。
BrailleLLM: Braille Instruction Tuning with Large Language Models for Braille Domain Tasks
- 基于语法树增强盲文数据，缓解低资源困境
- 引入盲文知识微调，翻译准确率显著提升
- 支持中英盲文、公式转换，适合无障碍研究者
盲文在视障人士教育与信息获取中至关重要，但面临数据稀缺和混合文本语义模糊的挑战。本文构建了含数学公式的英/中文盲文混合数据集（EBMD/CBMD），提出面向盲文数据的语法树增强方法。针对传统微调在盲文任务中表现不佳的问题，提出基于盲文知识的微调（BKFT），降低盲文上下文特征的学习难度。BrailleLLM通过指令微调实现统一盲文翻译、公式转盲文及混合文本转换。实验表明，BKFT在盲文翻译场景下显著优于传统微调。开源的数据集与方法为低资源多语言盲文研究奠定基础。
原文摘要 · Abstract (English)
Braille plays a vital role in education and information accessibility for visually impaired individuals. However, Braille information processing faces challenges such as data scarcity and ambiguities in mixed-text contexts. We construct English and Chinese Braille Mixed Datasets (EBMD/CBMD) with mathematical formulas to support diverse Braille domain research, and propose a syntax tree-based augmentation method tailored for Braille data. To address the underperformance of traditional fine-tuning methods in Braille-related tasks, we investigate Braille Knowledge-Based Fine-Tuning (BKFT), which reduces the learning difficulty of Braille contextual features. BrailleLLM employs BKFT via instruction tuning to achieve unified Braille translation, formula-to-Braille conversion, and mixed-text translation. Experiments demonstrate that BKFT achieves significant performance improvements over conventional fine-tuning in Braille translation scenarios. Our open-sourced datasets and methodologies establish a foundation for low-resource multilingual Braille research.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。