<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="joshi-etal-2026-causal">
    <titleInfo>
        <title>Causal Foundations for Interpretability: What Your Methods Actually Identify</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shruti</namePart>
        <namePart type="family">Joshi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aaron</namePart>
        <namePart type="family">Mueller</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Patrik</namePart>
        <namePart type="family">Reizinger</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dhanya</namePart>
        <namePart type="family">Sridhar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ana</namePart>
            <namePart type="family">Marasović</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Goran</namePart>
            <namePart type="family">Glavaš</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-463-7</identifier>
    </relatedItem>
    <abstract>Interpretability findings on large language models often fail to generalise, and causal claims can outrun the evidence. A recurring source, we suggest, is a borrowed vocabulary: interpretability inherited the words of causality — “mechanisms”, “circuits”, “features” — without always inheriting the bookkeeping that keeps causal claims precise. This tutorial teaches that bookkeeping for practitioners. Participants leave able to take any interpretability result and answer three questions: what claim does this method license, what would strengthen the claim, and when will it generalise?</abstract>
    <identifier type="citekey">joshi-etal-2026-causal</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-tutorials.5/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>8</start>
            <end>9</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Causal Foundations for Interpretability: What Your Methods Actually Identify
%A Joshi, Shruti
%A Mueller, Aaron
%A Reizinger, Patrik
%A Sridhar, Dhanya
%Y Marasović, Ana
%Y Glavaš, Goran
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-463-7
%F joshi-etal-2026-causal
%X Interpretability findings on large language models often fail to generalise, and causal claims can outrun the evidence. A recurring source, we suggest, is a borrowed vocabulary: interpretability inherited the words of causality — “mechanisms”, “circuits”, “features” — without always inheriting the bookkeeping that keeps causal claims precise. This tutorial teaches that bookkeeping for practitioners. Participants leave able to take any interpretability result and answer three questions: what claim does this method license, what would strengthen the claim, and when will it generalise?
%U https://aclanthology.org/2026.emnlp-tutorials.5/
%P 8-9

Markdown (Informal)

[Causal Foundations for Interpretability: What Your Methods Actually Identify](https://aclanthology.org/2026.emnlp-tutorials.5/) (Joshi et al., EMNLP 2026)

• Causal Foundations for Interpretability: What Your Methods Actually Identify (Joshi et al., EMNLP 2026)

ACL

• Shruti Joshi, Aaron Mueller, Patrik Reizinger, and Dhanya Sridhar. 2026. Causal Foundations for Interpretability: What Your Methods Actually Identify. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts, pages 8–9, Budapest, Hungary. Association for Computational Linguistics.