@inproceedings{heiman-2025-accuracy,
title = "The Accuracy, Robustness, and Readability of {LLM}-Generated Sustainability-Related Word Definitions",
author = "Heiman, Alice",
editor = "Basile, Valerio and
Bosco, Cristina and
Grasso, Francesca and
Ibrohim, Muhammad Okky and
Skeppstedt, Maria and
Stede, Manfred",
booktitle = "Proceedings of the 1st Workshop on Ecology, Environment, and Natural Language Processing (NLP4Ecology2025)",
month = mar,
year = "2025",
address = "Tallinn, Estonia",
publisher = "University of Tartu Library",
url = "https://aclanthology.org/2025.nlp4ecology-1.21/",
pages = "104--109",
ISBN = "978-9908-53-114-4",
abstract = "A common language with shared standard definitions is essential for effective climate conversations. However, there is concern that LLMs may misrepresent and/or diversify climate-related terms. We compare 305 official IPCC glossary definitions with those generated by OpenAI{'}s GPT-4o-mini and investigate their adherence, robustness, and readability using a combination of SBERT sentence embeddings and statistical measures. The LLM definitions received average adherence and robustness scores of $0.58 \pm 0.15$ and $0.96 \pm 0.02$, respectively. Both sustainability-related terminologies remain challenging to read, with model-generated definitions varying mainly among words with multiple or ambiguous definitions. Thus, the results highlight the potential of LLMs to support environmental discourse while emphasizing the need to align model outputs with established terminology for clarity and consistency."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="heiman-2025-accuracy">
<titleInfo>
<title>The Accuracy, Robustness, and Readability of LLM-Generated Sustainability-Related Word Definitions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alice</namePart>
<namePart type="family">Heiman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Ecology, Environment, and Natural Language Processing (NLP4Ecology2025)</title>
</titleInfo>
<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">Francesca</namePart>
<namePart type="family">Grasso</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>University of Tartu Library</publisher>
<place>
<placeTerm type="text">Tallinn, Estonia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-9908-53-114-4</identifier>
</relatedItem>
<abstract>A common language with shared standard definitions is essential for effective climate conversations. However, there is concern that LLMs may misrepresent and/or diversify climate-related terms. We compare 305 official IPCC glossary definitions with those generated by OpenAI’s GPT-4o-mini and investigate their adherence, robustness, and readability using a combination of SBERT sentence embeddings and statistical measures. The LLM definitions received average adherence and robustness scores of 0.58 \pm 0.15 and 0.96 \pm 0.02, respectively. Both sustainability-related terminologies remain challenging to read, with model-generated definitions varying mainly among words with multiple or ambiguous definitions. Thus, the results highlight the potential of LLMs to support environmental discourse while emphasizing the need to align model outputs with established terminology for clarity and consistency.</abstract>
<identifier type="citekey">heiman-2025-accuracy</identifier>
<location>
<url>https://aclanthology.org/2025.nlp4ecology-1.21/</url>
</location>
<part>
<date>2025-03</date>
<extent unit="page">
<start>104</start>
<end>109</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Accuracy, Robustness, and Readability of LLM-Generated Sustainability-Related Word Definitions
%A Heiman, Alice
%Y Basile, Valerio
%Y Bosco, Cristina
%Y Grasso, Francesca
%Y Ibrohim, Muhammad Okky
%Y Skeppstedt, Maria
%Y Stede, Manfred
%S Proceedings of the 1st Workshop on Ecology, Environment, and Natural Language Processing (NLP4Ecology2025)
%D 2025
%8 March
%I University of Tartu Library
%C Tallinn, Estonia
%@ 978-9908-53-114-4
%F heiman-2025-accuracy
%X A common language with shared standard definitions is essential for effective climate conversations. However, there is concern that LLMs may misrepresent and/or diversify climate-related terms. We compare 305 official IPCC glossary definitions with those generated by OpenAI’s GPT-4o-mini and investigate their adherence, robustness, and readability using a combination of SBERT sentence embeddings and statistical measures. The LLM definitions received average adherence and robustness scores of 0.58 \pm 0.15 and 0.96 \pm 0.02, respectively. Both sustainability-related terminologies remain challenging to read, with model-generated definitions varying mainly among words with multiple or ambiguous definitions. Thus, the results highlight the potential of LLMs to support environmental discourse while emphasizing the need to align model outputs with established terminology for clarity and consistency.
%U https://aclanthology.org/2025.nlp4ecology-1.21/
%P 104-109
Markdown (Informal)
[The Accuracy, Robustness, and Readability of LLM-Generated Sustainability-Related Word Definitions](https://aclanthology.org/2025.nlp4ecology-1.21/) (Heiman, NLP4Ecology 2025)
ACL