低资源语言能从彼此间学到什么？
What Can Low Resource Languages Learn From Each Other?
查看机构详情
- IIT Delhi（印度理工学院德里分校）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
针对低资源语言OCR数据稀缺问题，提出PSMC框架，通过融合语言特定专家实现知识迁移，在10种印度文字上使词识别率平均提升约2%。
中文摘要 AI 辅助
尽管视觉语言模型（VLMs）发展迅速，但其语言覆盖范围仍主要局限于高资源语言，致使全球7000多种现存语言中的大多数被置于日益扩大的数字鸿沟的不利一侧。这种差距在光学字符识别（OCR）领域尤为显著，低资源文字缺乏传统缩放定律所需的海量数据集。我们在极端数据稀缺 regime（<1万张真实图像、<25万张合成图像）下研究OCR适配，发现常规微调策略常触及性能天花板。我们的关键发现揭示了语言特定适配中的结构低效性：专用模型的高层会分化以捕捉独特的文字细微差别，而低层则学习到冗余、高度相似的特征。基于此观察，我们提出PSMC（预训练、专用化、融合与协同训练）这一数据高效框架，利用跨文字的“迁移效应”。该方法首先从高资源基础模型中衍生出语言特定专家，再采用任务算术将这些专家融合为统一、高性能的多语言主干。对10种印度文字（支持20多种语言）的广泛评估显示，PSMC在不增加参数数量的情况下，相比单个专用模型实现了约2%的词识别率（WRR）平均提升。我们的结果表明，在融合潜在空间中进行联合训练促进了建设性的知识迁移，使所有组成文字受益，为包容性VLM开发提供了可扩展路径。源代码和数据集将在出版后发布。
英文摘要
Despite the rapid advancement of Vision-Language Models (VLMs), their linguistic reach remains largely confined to high-resource languages, leaving the majority of the world's 7,000+ living languages on the wrong side of a growing digital divide. This disparity is especially pronounced in Optical Character Recognition (OCR), where low-resource scripts lack the massive datasets required for traditional scaling laws. We investigate OCR adaptation in extreme data-scarce regimes (<10K real and <250K synthetic images), demonstrating that conventional fine-tuning strategies often reach a performance ceiling. Our key finding reveals a structural inefficiency in language-specific adaptation: while higher layers of specialized models diverge to capture unique script nuances, the lower layers learn redundant, highly similar features. Motivated by this observation, we propose PSMC (Pre-train, Specialize, Merge, and Co-train), a data-efficient framework that capitalizes on a cross-script "transfer effect". Our approach first derives language-specific experts from a high-resource base model, then employs task arithmetic to fuse these experts into a unified, high-performance multilingual back- bone. Extensive evaluation across 10 Indian scripts (supporting 20+ languages) shows that PSMC achieves a ~2% average improvement in Word Recognition Rate (WRR) over individual specialist models without increasing parameter count. Our results indicate that joint training in the merged latent space facilitates a constructive knowledge transfer that benefits all constituent scripts, providing a scalable pathway for inclusive VLM development. Source code and datasets will be released post publication.
