Publication:

CHATREPORT: Democratizing Sustainability Disclosure Analysis through LLM-based Tools

Date

Date

Date
2023
Conference or Workshop Item
Published version
cris.lastimport.scopus2025-06-29T03:45:02Z
cris.virtual.orcidhttps://orcid.org/0000-0001-8029-4106
cris.virtual.orcidhttps://orcid.org/0000-0001-5983-2360
cris.virtualsource.orcid5b89af53-a78a-4012-bb2a-48096581f6e3
cris.virtualsource.orcid0331cda6-e903-4e22-9b44-f89f54f581dc
dc.contributor.institutionUniversity of Zurich
dc.date.accessioned2025-02-03T15:12:13Z
dc.date.available2025-02-03T15:12:13Z
dc.date.issued2023-12-30
dc.description.abstract

In the face of climate change, are companies really taking substantial steps toward more sustainable operations? A comprehensive answer lies in the dense, information-rich landscape of corporate sustainability reports. However, the sheer volume and complexity of these reports make human analysis very costly. Therefore, only a few entities worldwide have the resources to analyze these reports at scale, which leads to a lack of transparency in sustainability reporting. Empowering stakeholders with LLM-based automatic analysis tools can be a promising way to democratize sustainability report analysis. However, developing such tools is challenging due to (1) the hallucination of LLMs and (2) the inefficiency of bringing domain experts into the AI development loop. In this paper, we introduce ChatReport, a novel LLM-based system to automate the analysis of corporate sustainability reports, addressing existing challenges by (1) making the answers traceable to reduce the harm of hallucination and (2) actively involving domain experts in the development loop.

dc.identifier.doi10.18653/v1/2023.emnlp-demo.3
dc.identifier.scopus2-s2.0-85184654953
dc.identifier.urihttps://www.zora.uzh.ch/handle/20.500.14742/227681
dc.language.isoeng
dc.subject.ddc330 Economics
dc.title

CHATREPORT: Democratizing Sustainability Disclosure Analysis through LLM-based Tools

dc.typeconference_item
dcterms.accessRightsinfo:eu-repo/semantics/openAccess
dcterms.bibliographicCitation.journaltitleProceedings of the Conference on Empirical Methods in Natural Language Processing
dcterms.bibliographicCitation.originalpublishernameAssociation for Computational Linguistics
dcterms.bibliographicCitation.pageend51
dcterms.bibliographicCitation.pagestart21
dspace.entity.typePublicationen
oairecerif.event.countrySingapore
oairecerif.event.endDate2023-12-10
oairecerif.event.placeSingapore
oairecerif.event.startDate2023-12-06
uzh.contributor.affiliationUniversity of Zurich, ETH Zürich
uzh.contributor.affiliationUniversity of Oxford, Council on Economic Policies
uzh.contributor.affiliationUniversity of Zurich
uzh.contributor.affiliationFriedrich-Alexander-Universität Erlangen-Nürnberg
uzh.contributor.affiliationUniversity of Zurich
uzh.contributor.affiliationUniversity of Zurich
uzh.contributor.affiliationETH Zürich
uzh.contributor.affiliationUniversity of Zurich, Swiss Federal Institute of Aquatic Science and Technology
uzh.contributor.affiliationUniversity of Zurich
uzh.contributor.affiliationFriedrich-Alexander-Universität Erlangen-Nürnberg
uzh.contributor.affiliationUniversity of Zurich, ETH Zürich
uzh.contributor.affiliationUniversity of Zurich
uzh.contributor.affiliationUniversity of Zurich, Swiss Finance Institute
uzh.contributor.authorNi, Jingwei
uzh.contributor.authorBingler, Julia
uzh.contributor.authorColesanti Senni, Chiara
uzh.contributor.authorKraus, Mathias
uzh.contributor.authorGostlow, Glen
uzh.contributor.authorSchimanski, Tobias
uzh.contributor.authorStammbach, Dominik
uzh.contributor.authorAshraf Vaghefi, Saeid
uzh.contributor.authorWang, Qian
uzh.contributor.authorWebersinke, Nicolas
uzh.contributor.authorWekhof, Tobias
uzh.contributor.authorYu, Tingyu
uzh.contributor.authorLeippold, Markus
uzh.contributor.correspondenceYes
uzh.contributor.correspondenceNo
uzh.contributor.correspondenceNo
uzh.contributor.correspondenceNo
uzh.contributor.correspondenceNo
uzh.contributor.correspondenceNo
uzh.contributor.correspondenceNo
uzh.contributor.correspondenceNo
uzh.contributor.correspondenceNo
uzh.contributor.correspondenceNo
uzh.contributor.correspondenceNo
uzh.contributor.correspondenceNo
uzh.contributor.correspondenceNo
uzh.document.availabilitypublished_version
uzh.eprint.datestamp2025-02-03 15:12:13
uzh.eprint.lastmod2025-06-29 03:45:02
uzh.eprint.statusChange2025-02-03 15:12:13
uzh.event.presentationTypepaper
uzh.event.titleThe 2023 Conference on Empirical Methods in Natural Language Processing
uzh.event.typeconference
uzh.harvester.ethYes
uzh.harvester.nbNo
uzh.identifier.doi10.5167/uzh-270669
uzh.jdb.eprintsId48197
uzh.oastatus.unpaywallhybrid
uzh.oastatus.zoraHybrid
uzh.publication.citationNi, Jingwei; Bingler, Julia; Colesanti Senni, Chiara; Kraus, Mathias; Gostlow, Glen; Schimanski, Tobias; Stammbach, Dominik; Ashraf Vaghefi, Saeid; Wang, Qian; Webersinke, Nicolas; Wekhof, Tobias; Yu, Tingyu; Leippold, Markus (2023). CHATREPORT: Democratizing Sustainability Disclosure Analysis through LLM-based Tools. In: The 2023 Conference on Empirical Methods in Natural Language Processing, Singapore, Singapore, 6 December 2023 - 10 December 2023. Association for Computational Linguistics, 21-51.
uzh.publication.freeAccessAtdoi
uzh.publication.originalworkoriginal
uzh.publication.publishedStatusfinal
uzh.publication.scopedisciplinebased
uzh.publication.seriesTitleProceedings of the Conference on Empirical Methods in Natural Language Processing
uzh.scopus.impact6
uzh.scopus.subjectsComputational Theory and Mathematics
uzh.scopus.subjectsComputer Science Applications
uzh.scopus.subjectsInformation Systems
uzh.workflow.chairSubjectoecIBF1
uzh.workflow.doajuzh.workflow.doaj.false
uzh.workflow.eprintid270669
uzh.workflow.fulltextStatuspublic
uzh.workflow.revisions26
uzh.workflow.rightsCheckoffen
uzh.workflow.sourceCrossref:10.18653/v1/2023.emnlp-demo.3
uzh.workflow.statusarchive
Files

Original bundle

Name:
ZORA_2023_emnlp_demo_3.pdf
Size:
595.46 KB
Format:
Adobe Portable Document Format
Publication available in collections: