<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="neo-etal-2026-spectra">
    <titleInfo>
        <title>Spectra: A Mechanistic Interpretability Library for Vision-Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Clement</namePart>
        <namePart type="family">Neo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yongsen</namePart>
        <namePart type="family">Zheng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kwok-Yan</namePart>
        <namePart type="family">Lam</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Luke</namePart>
        <namePart type="family">Ong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Greg</namePart>
            <namePart type="family">Durrett</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ping</namePart>
            <namePart type="family">Jian</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-392-0</identifier>
    </relatedItem>
    <abstract>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.</abstract>
    <identifier type="citekey">neo-etal-2026-spectra</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-demo.78/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>794</start>
            <end>803</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Spectra: A Mechanistic Interpretability Library for Vision-Language Models
%A Neo, Clement
%A Zheng, Yongsen
%A Lam, Kwok-Yan
%A Ong, Luke
%Y Durrett, Greg
%Y Jian, Ping
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-392-0
%F neo-etal-2026-spectra
%X 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.
%U https://aclanthology.org/2026.acl-demo.78/
%P 794-803

Markdown (Informal)

[Spectra: A Mechanistic Interpretability Library for Vision-Language Models](https://aclanthology.org/2026.acl-demo.78/) (Neo et al., ACL 2026)

• Spectra: A Mechanistic Interpretability Library for Vision-Language Models (Neo et al., ACL 2026)

ACL

• Clement Neo, Yongsen Zheng, Kwok-Yan Lam, and Luke Ong. 2026. Spectra: A Mechanistic Interpretability Library for Vision-Language Models. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pages 794–803, San Diego, California, United States. Association for Computational Linguistics.