← 研踪 PaperTrailACL Anthology · ACL 2026:acl:2026.acl-demo.78 · 记录 #1
Spectra: A Mechanistic Interpretability Library for Vision-Language Models
来源日期（仅到月份） 2026-07
来源记录日期 2026-07
雷达观测 2026-11-01 22:08
摘要
Vision-Language Models (VLMs) have become increasingly important in AI applications, yet interpretability tools for these models lag behind those available for text-only language models. While libraries like TransformerLens have enabled significant progress in understanding language models, existing tools for VLMs are limited to basic activation probing and saving. We introduce Spectra, a library specifically designed for mechanistic interpretability of VLMs that provides unified abstractions for activation patching, attention pattern analysis, and meta-functions across diverse VLM architectures. Built on HuggingFace’s Transformers, our library handles architecture-specific complexities through per-checkpoint configurations while maintaining a simple, high-level interface. We demonstrate the library’s capabilities by performing interpretability experiments on a counting task, showing how researchers can easily perform experiments that were previously cumbersome to do. The library currently supports Qwen2.5-VL, Qwen3-VL, LLaVA 1.5 and SmolVLM, with a design that facilitates extension to additional architectures. The library can be found at github.com/clemneo/vlm-spectra.
论文发现出处
这些页面提供论文线索，不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化，不是作者修订号。来源日期仅到月份或年份时，按该月或该年首日存档。
记录 #1 · 2026-07 · 最新观测版本
Spectra: A Mechanistic Interpretability Library for Vision-Language Models
Vision-Language Models (VLMs) have become increasingly important in AI applications, yet interpretability tools for these models lag behind those available for text-only language models. While libraries like TransformerLens have enabled significant progress in understanding language models, existing tools for VLMs are limited to basic activation probing and saving. We introduce Spectra, a library specifically designed for mechanistic interpretability of VLMs that provides unified abstractions for activation patching, attention pattern analysis, and meta-functions across diverse VLM architectures. Built on HuggingFace’s Transformers, our library handles architecture-specific complexities through per-checkpoint configurations while maintaining a simple, high-level interface. We demonstrate the library’s capabilities by performing interpretability experiments on a counting task, showing how researchers can easily perform experiments that were previously cumbersome to do. The library currently supports Qwen2.5-VL, Qwen3-VL, LLaVA 1.5 and SmolVLM, with a design that facilitates extension to additional architectures. The library can be found at github.com/clemneo/vlm-spectra.
查看此版本解读 →查看此版本原文 ↗