策展人引导的多语言艺术描述对盲人和低视力观众的小型视觉语言模型试点研究
A Pilot Study on Curator-Guided Multilingual Art Description for Blind and Low-Vision Audiences with Small Vision-Language Models
AI总结：
本研究使用小型视觉语言模型Qwen2.5-VL-3B-Instruct，通过策展人引导的方式为盲人和低视力观众生成德语、罗马尼亚语和塞尔维亚语的多语言艺术描述，发现语言特定适配器在控制性和视觉基础描述质量上优于多语言适配器。
摘要：
盲人和低视力（BLV）观众在视觉艺术描述方面仍然服务不足，尤其是在跨语言和博物馆环境中，隐私和知识产权限制可能倾向于使用小型本地视觉语言模型（VLM）。本试点研究使用Qwen2.5-VL-3B-Instruct，针对德语、罗马尼亚语和塞尔维亚语，调查了策展人引导的多语言艺术描述。我们从艺术品图像和元数据构建了一个平行的BLV导向字幕语料库，并在固定骨干网络和训练预算下，比较了语言特定的LoRA适配器与单个多语言适配器。评估结合了自动词汇和基于嵌入的指标，以及针对小型罗马尼亚BLV试点研究校准的LLM作为评判协议。在我们的试点设置下，语言特定适配器在罗马尼亚语和塞尔维亚语上表现出更稳定的可控性和视觉基础描述质量，而多语言适配器在德语上仍具有竞争力。我们将这些发现视为小型本地VLM的部署导向证据，并强调在得出关于多语言可访问性的总体结论之前，需要进行更大规模的BLV用户研究和更广泛的语言覆盖。
英文摘要：
Blind and low-vision (BLV) audiences remain underserved by visual art descriptions, particularly across languages and in museum settings where privacy and intellectual-property constraints may favour small on-premise vision-language models (VLMs). This pilot study investigates curator-guided multilingual art description with Qwen2.5-VL-3B-Instruct for German, Romanian, and Serbian. We construct a parallel BLV-oriented caption corpus from artwork images and metadata, and compare language-specific LoRA adapters with a single multilingual adapter under a fixed backbone and training budget. Evaluation combines automatic lexical and embedding-based metrics with an LLM-as-Judge protocol calibrated against a small Romanian BLV pilot study. Under our pilot setup, language-specific adapters show more stable controllability and visually grounded description quality for Romanian and Serbian, while multilingual adaptation remains competitive in German. We frame these findings as deployment-oriented evidence for small on-premise VLMs, and highlight the need for larger BLV user studies and broader language coverage before drawing general conclusions about multilingual accessibility.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
