@inproceedings{biswas-etal-2025-evaluating,
title = "Evaluating Retrieval Augmented Generation to Communicate {UK} Climate Change Information",
author = "Biswas, Arjun and
Chahout, Hatim and
Pigram, Tristan and
Dong, Hang and
Williams, Hywel T.P. and
Fung, Fai and
Xie, Hailun",
editor = "Dutia, Kalyan and
Henderson, Peter and
Leippold, Markus and
Manning, Christoper and
Morio, Gaku and
Muccione, Veruska and
Ni, Jingwei and
Schimanski, Tobias and
Stammbach, Dominik and
Singh, Alok and
Su, Alba (Ruiran) and
A. Vaghefi, Saeid",
booktitle = "Proceedings of the 2nd Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.climatenlp-1.9/",
doi = "10.18653/v1/2025.climatenlp-1.9",
pages = "126--141",
ISBN = "979-8-89176-259-6",
abstract = "There is a huge demand for information about climate change across all sectors as societies seek to mitigate and adapt to its impacts. However, the volume and complexity of climate information, which takes many formats including numerical, text, and tabular data, can make good information hard to access. Here we use Large Language Models (LLMs) and Retrieval Augmented Generation (RAG) to create an AI agent that provides accurate and complete information from the United Kingdom Climate Projections 2018 (UKCP18) data archive. To overcome the problematic hallucinations associated with LLMs, four phases of experiments were performed to optimize different components of our RAG framework, combining various recent retrieval strategies. Performance was evaluated using three statistical metrics (faithfulness, relevance, coverage) as well as human evaluation by subject matter experts. Results show that the best model significantly outperforms a generic LLM (GPT-3.5) and has high-quality outputs with positive ratings by human experts. The UKCP Chatbot developed here will enable access at scale to the UKCP18 climate archives, offering an important case study of using RAG-based LLM systems to communicate climate information."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="biswas-etal-2025-evaluating">
<titleInfo>
<title>Evaluating Retrieval Augmented Generation to Communicate UK Climate Change Information</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arjun</namePart>
<namePart type="family">Biswas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hatim</namePart>
<namePart type="family">Chahout</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tristan</namePart>
<namePart type="family">Pigram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hang</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hywel</namePart>
<namePart type="given">T.P.</namePart>
<namePart type="family">Williams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fai</namePart>
<namePart type="family">Fung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hailun</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kalyan</namePart>
<namePart type="family">Dutia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Henderson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="family">Leippold</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christoper</namePart>
<namePart type="family">Manning</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaku</namePart>
<namePart type="family">Morio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veruska</namePart>
<namePart type="family">Muccione</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingwei</namePart>
<namePart type="family">Ni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tobias</namePart>
<namePart type="family">Schimanski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dominik</namePart>
<namePart type="family">Stammbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alok</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alba</namePart>
<namePart type="given">(Ruiran)</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saeid</namePart>
<namePart type="family">A. Vaghefi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-259-6</identifier>
</relatedItem>
<abstract>There is a huge demand for information about climate change across all sectors as societies seek to mitigate and adapt to its impacts. However, the volume and complexity of climate information, which takes many formats including numerical, text, and tabular data, can make good information hard to access. Here we use Large Language Models (LLMs) and Retrieval Augmented Generation (RAG) to create an AI agent that provides accurate and complete information from the United Kingdom Climate Projections 2018 (UKCP18) data archive. To overcome the problematic hallucinations associated with LLMs, four phases of experiments were performed to optimize different components of our RAG framework, combining various recent retrieval strategies. Performance was evaluated using three statistical metrics (faithfulness, relevance, coverage) as well as human evaluation by subject matter experts. Results show that the best model significantly outperforms a generic LLM (GPT-3.5) and has high-quality outputs with positive ratings by human experts. The UKCP Chatbot developed here will enable access at scale to the UKCP18 climate archives, offering an important case study of using RAG-based LLM systems to communicate climate information.</abstract>
<identifier type="citekey">biswas-etal-2025-evaluating</identifier>
<identifier type="doi">10.18653/v1/2025.climatenlp-1.9</identifier>
<location>
<url>https://aclanthology.org/2025.climatenlp-1.9/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>126</start>
<end>141</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Retrieval Augmented Generation to Communicate UK Climate Change Information
%A Biswas, Arjun
%A Chahout, Hatim
%A Pigram, Tristan
%A Dong, Hang
%A Williams, Hywel T.P.
%A Fung, Fai
%A Xie, Hailun
%Y Dutia, Kalyan
%Y Henderson, Peter
%Y Leippold, Markus
%Y Manning, Christoper
%Y Morio, Gaku
%Y Muccione, Veruska
%Y Ni, Jingwei
%Y Schimanski, Tobias
%Y Stammbach, Dominik
%Y Singh, Alok
%Y Su, Alba (Ruiran)
%Y A. Vaghefi, Saeid
%S Proceedings of the 2nd Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-259-6
%F biswas-etal-2025-evaluating
%X There is a huge demand for information about climate change across all sectors as societies seek to mitigate and adapt to its impacts. However, the volume and complexity of climate information, which takes many formats including numerical, text, and tabular data, can make good information hard to access. Here we use Large Language Models (LLMs) and Retrieval Augmented Generation (RAG) to create an AI agent that provides accurate and complete information from the United Kingdom Climate Projections 2018 (UKCP18) data archive. To overcome the problematic hallucinations associated with LLMs, four phases of experiments were performed to optimize different components of our RAG framework, combining various recent retrieval strategies. Performance was evaluated using three statistical metrics (faithfulness, relevance, coverage) as well as human evaluation by subject matter experts. Results show that the best model significantly outperforms a generic LLM (GPT-3.5) and has high-quality outputs with positive ratings by human experts. The UKCP Chatbot developed here will enable access at scale to the UKCP18 climate archives, offering an important case study of using RAG-based LLM systems to communicate climate information.
%R 10.18653/v1/2025.climatenlp-1.9
%U https://aclanthology.org/2025.climatenlp-1.9/
%U https://doi.org/10.18653/v1/2025.climatenlp-1.9
%P 126-141
Markdown (Informal)
[Evaluating Retrieval Augmented Generation to Communicate UK Climate Change Information](https://aclanthology.org/2025.climatenlp-1.9/) (Biswas et al., ClimateNLP 2025)
ACL