<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="drechsel-herbold-2026-gradiend">
    <titleInfo>
        <title>The GRADIEND Python Package: An End-to-End System for Gradient-Based Feature Learning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jonathan</namePart>
        <namePart type="family">Drechsel</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Steffen</namePart>
        <namePart type="family">Herbold</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: System Demonstrations</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Sweta</namePart>
            <namePart type="family">Agrawal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alberto</namePart>
            <namePart type="family">Abad</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">979-8-89176-461-3</identifier>
    </relatedItem>
    <abstract>We present ‘gradiend‘, an open-source Python package that operationalizes the GRADIEND method for learning feature directions from factual-counterfactual MLM and CLM gradients in language models. The package provides a unified workflow for feature-related data creation, training, evaluation, visualization, persistent model rewriting via controlled weight updates, and multi-feature comparison. We demonstrate ‘gradiend‘ through an English pronoun running example, a semantic sentiment use case that evaluates lexical generalization to held-out target words, and a large-scale feature comparison.</abstract>
    <identifier type="citekey">drechsel-herbold-2026-gradiend</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-demos.18/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>189</start>
            <end>198</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T The GRADIEND Python Package: An End-to-End System for Gradient-Based Feature Learning
%A Drechsel, Jonathan
%A Herbold, Steffen
%Y Agrawal, Sweta
%Y Abad, Alberto
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-461-3
%F drechsel-herbold-2026-gradiend
%X We present ‘gradiend‘, an open-source Python package that operationalizes the GRADIEND method for learning feature directions from factual-counterfactual MLM and CLM gradients in language models. The package provides a unified workflow for feature-related data creation, training, evaluation, visualization, persistent model rewriting via controlled weight updates, and multi-feature comparison. We demonstrate ‘gradiend‘ through an English pronoun running example, a semantic sentiment use case that evaluates lexical generalization to held-out target words, and a large-scale feature comparison.
%U https://aclanthology.org/2026.emnlp-demos.18/
%P 189-198

Markdown (Informal)

[The GRADIEND Python Package: An End-to-End System for Gradient-Based Feature Learning](https://aclanthology.org/2026.emnlp-demos.18/) (Drechsel & Herbold, EMNLP 2026)

• The GRADIEND Python Package: An End-to-End System for Gradient-Based Feature Learning (Drechsel & Herbold, EMNLP 2026)

ACL

• Jonathan Drechsel and Steffen Herbold. 2026. The GRADIEND Python Package: An End-to-End System for Gradient-Based Feature Learning. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 189–198, Budapest, Hungary. Association for Computational Linguistics.