<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vallego-etal-2026-stories">
    <titleInfo>
        <title>What Stories Do Language Models Tell About Nature? A Multi Layer Evaluation Framework for Ecological Alignment</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jorge</namePart>
        <namePart type="family">Vallego</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Eleanor</namePart>
        <namePart type="family">Tiernan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mah</namePart>
        <namePart type="family">Rukh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mariana</namePart>
        <namePart type="family">Roccia</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sabina</namePart>
        <namePart type="given">Fiebig</namePart>
        <namePart type="family">Lord</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2nd Workshop on Ecology, Environment, and Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Francesca</namePart>
            <namePart type="family">Grasso</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Valerio</namePart>
            <namePart type="family">Basile</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Cristina</namePart>
            <namePart type="family">Bosco</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Muhammad</namePart>
            <namePart type="given">Okky</namePart>
            <namePart type="family">Ibrohim</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Skeppstedt</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Manfred</namePart>
            <namePart type="family">Stede</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>European Language Resources Association</publisher>
            <place>
                <placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Large language models increasingly generate environmental discourse, yet there is no standardised framework for evaluating the ecological narratives they produce. We introduce a structured prompt corpus and a reproducible multi layer evaluation framework grounded in ecolinguistic theory, operationalising five dimensions of ecological alignment: anthropocentrism, agency attribution, erasure of non human impacts, evaluation of growth, and responsibility framing. The framework integrates human judgement, an ecosophy aligned model judge, and automated semantic metrics, and is applied to outputs from ChatGPT, DeepSeek, and Ecophora, our ecosophy guided model. Ecophora achieves the highest alignment across all layers, with near ceiling judge scores of 159/160 and 142/160, together with the strongest automated composite performance. Divergences between automated metrics and holistic judgement indicate that ecological vocabulary alone does not guarantee ecological reasoning. The proposed framework provides a scalable methodology for benchmarking ecological alignment and assessing narrative shifts in language models.</abstract>
    <identifier type="citekey">vallego-etal-2026-stories</identifier>
    <identifier type="doi">10.63317/3ah3mdj5br6k</identifier>
    <location>
        <url>https://aclanthology.org/2026.nlp4ecology-1.6/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>60</start>
            <end>68</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T What Stories Do Language Models Tell About Nature? A Multi Layer Evaluation Framework for Ecological Alignment
%A Vallego, Jorge
%A Tiernan, Eleanor
%A Rukh, Mah
%A Roccia, Mariana
%A Lord, Sabina Fiebig
%Y Grasso, Francesca
%Y Basile, Valerio
%Y Bosco, Cristina
%Y Ibrohim, Muhammad Okky
%Y Skeppstedt, Maria
%Y Stede, Manfred
%S Proceedings of the 2nd Workshop on Ecology, Environment, and Natural Language Processing
%D 2026
%8 May
%I European Language Resources Association
%C Palma de Mallorca, Spain
%F vallego-etal-2026-stories
%X Large language models increasingly generate environmental discourse, yet there is no standardised framework for evaluating the ecological narratives they produce. We introduce a structured prompt corpus and a reproducible multi layer evaluation framework grounded in ecolinguistic theory, operationalising five dimensions of ecological alignment: anthropocentrism, agency attribution, erasure of non human impacts, evaluation of growth, and responsibility framing. The framework integrates human judgement, an ecosophy aligned model judge, and automated semantic metrics, and is applied to outputs from ChatGPT, DeepSeek, and Ecophora, our ecosophy guided model. Ecophora achieves the highest alignment across all layers, with near ceiling judge scores of 159/160 and 142/160, together with the strongest automated composite performance. Divergences between automated metrics and holistic judgement indicate that ecological vocabulary alone does not guarantee ecological reasoning. The proposed framework provides a scalable methodology for benchmarking ecological alignment and assessing narrative shifts in language models.
%R 10.63317/3ah3mdj5br6k
%U https://aclanthology.org/2026.nlp4ecology-1.6/
%U https://doi.org/10.63317/3ah3mdj5br6k
%P 60-68

Markdown (Informal)

[What Stories Do Language Models Tell About Nature? A Multi Layer Evaluation Framework for Ecological Alignment](https://aclanthology.org/2026.nlp4ecology-1.6/) (Vallego et al., NLP4Ecology 2026)

• What Stories Do Language Models Tell About Nature? A Multi Layer Evaluation Framework for Ecological Alignment (Vallego et al., NLP4Ecology 2026)

ACL

• Jorge Vallego, Eleanor Tiernan, Mah Rukh, Mariana Roccia, and Sabina Fiebig Lord. 2026. What Stories Do Language Models Tell About Nature? A Multi Layer Evaluation Framework for Ecological Alignment. In Proceedings of the 2nd Workshop on Ecology, Environment, and Natural Language Processing, pages 60–68, Palma de Mallorca, Spain. European Language Resources Association.