<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="eidt-feldhus-2026-simplifying">
    <titleInfo>
        <title>Simplifying Outcomes of Language Model Component Analyses with ELIA</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Aaron</namePart>
        <namePart type="given">Louis</namePart>
        <namePart type="family">Eidt</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nils</namePart>
        <namePart type="family">Feldhus</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Danilo</namePart>
            <namePart type="family">Croce</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jochen</namePart>
            <namePart type="family">Leidner</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nafise</namePart>
            <namePart type="given">Sadat</namePart>
            <namePart type="family">Moosavi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Rabat, Marocco</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-382-1</identifier>
    </relatedItem>
    <abstract>While mechanistic interpretability has developed powerful tools to analyze the internal workings of Large Language Models (LLMs), their complexity has created an accessibility gap, limiting their use to specialists. We address this challenge by designing, building, and evaluating ELIA (Explainable Language Interpretability Analysis), an interactive web application that simplifies the outcomes of various language model component analyses for a broader audience. The system integrates three key techniques – Attribution Analysis, Function Vector Analysis, and Circuit Tracing – and introduces a novel methodology: using a vision-language model to automatically generate natural language explanations (NLEs) for the complex visualizations produced by these methods. The effectiveness of this approach was empirically validated through a mixed-methods user study, which revealed a clear preference for interactive, explorable interfaces over simpler, static visualizations. A key finding was that the AI-powered explanations successfully bridged the knowledge gap for non-experts; a statistical analysis showed no significant correlation between a user’s prior LLM experience and their comprehension scores, indicating that the system effectively leveled the playing field. We conclude that an AI system can indeed simplify complex model analyses, but its true power is unlocked when paired with thoughtful, user-centered design that prioritizes interactivity, specificity, and narrative guidance.</abstract>
    <identifier type="citekey">eidt-feldhus-2026-simplifying</identifier>
    <location>
        <url>https://aclanthology.org/2026.eacl-demo.9/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>111</start>
            <end>128</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Simplifying Outcomes of Language Model Component Analyses with ELIA
%A Eidt, Aaron Louis
%A Feldhus, Nils
%Y Croce, Danilo
%Y Leidner, Jochen
%Y Moosavi, Nafise Sadat
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Marocco
%@ 979-8-89176-382-1
%F eidt-feldhus-2026-simplifying
%X While mechanistic interpretability has developed powerful tools to analyze the internal workings of Large Language Models (LLMs), their complexity has created an accessibility gap, limiting their use to specialists. We address this challenge by designing, building, and evaluating ELIA (Explainable Language Interpretability Analysis), an interactive web application that simplifies the outcomes of various language model component analyses for a broader audience. The system integrates three key techniques – Attribution Analysis, Function Vector Analysis, and Circuit Tracing – and introduces a novel methodology: using a vision-language model to automatically generate natural language explanations (NLEs) for the complex visualizations produced by these methods. The effectiveness of this approach was empirically validated through a mixed-methods user study, which revealed a clear preference for interactive, explorable interfaces over simpler, static visualizations. A key finding was that the AI-powered explanations successfully bridged the knowledge gap for non-experts; a statistical analysis showed no significant correlation between a user’s prior LLM experience and their comprehension scores, indicating that the system effectively leveled the playing field. We conclude that an AI system can indeed simplify complex model analyses, but its true power is unlocked when paired with thoughtful, user-centered design that prioritizes interactivity, specificity, and narrative guidance.
%U https://aclanthology.org/2026.eacl-demo.9/
%P 111-128

Markdown (Informal)

[Simplifying Outcomes of Language Model Component Analyses with ELIA](https://aclanthology.org/2026.eacl-demo.9/) (Eidt & Feldhus, EACL 2026)

• Simplifying Outcomes of Language Model Component Analyses with ELIA (Eidt & Feldhus, EACL 2026)

ACL

• Aaron Louis Eidt and Nils Feldhus. 2026. Simplifying Outcomes of Language Model Component Analyses with ELIA. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations), pages 111–128, Rabat, Marocco. Association for Computational Linguistics.