发现视觉语言模型中对文化敏感的神经元，揭示其位置与作用机制。
Finding Culture-Sensitive Neurons in Vision-Language Models
- 通过激活分析识别出对特定文化输入敏感的神经元。
- 剔除这些神经元后，对应文化问答性能显著下降，其他文化影响小。
- 提出新方法ConAct，比传统方法更有效识别文化敏感神经元。
尽管表现优异，视觉语言模型（VLMs）在涉及文化背景的输入上仍存在困难。为理解其如何处理文化相关信息，我们研究了文化敏感神经元——即对特定文化情境输入具有偏好性激活的神经元。基于CVQA基准，我们识别出具有文化选择性的神经元，并通过关闭这些神经元进行诊断测试。在三个VLMs、25个文化群体上的实验表明，移除特定文化对应的神经元会显著降低该文化问答性能，而对其他文化影响较小。此外，我们提出一种新的基于边距的筛选方法：对比激活边距（ConAct），其在识别文化敏感神经元方面优于基于概率和熵的方法。层间分析显示，这类神经元并非均匀分布，而是以模型依赖的方式聚集在特定解码器层中。
原文摘要 · Abstract (English)
Despite their impressive performance, vision-language models (VLMs) still struggle on culturally situated inputs. To understand how VLMs process culturally grounded information, we study the presence of culture-sensitive neurons, i.e., neurons whose activations show preferential sensitivity to inputs associated with particular cultural contexts. We examine whether such neurons are important for culturally diverse visual question answering and where they are located. Using the CVQA benchmark, we identify neurons of culture selectivity and perform diagnostic tests by deactivating the neurons flagged by various identification methods. Experiments on three VLMs across 25 cultural groups demonstrate the existence of neurons whose ablation disproportionately harms performance on questions about the corresponding cultures, while having limited effects on others. Moreover, we introduce a new margin-based selector Contrastive Activation Margin (ConAct) and show that it outperforms probability- and entropy-based methods in identifying neurons associated with cultural selectivity. Finally, our layer-wise analyses reveal that such neurons are not uniformly distributed: they cluster in specific decoder layers in a model-dependent way.
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。