Gespeichert in:
| Beteiligte Personen: | , , , , , , , |
|---|---|
| Format: | Elektronisch E-Book |
| Sprache: | Englisch |
| Veröffentlicht: |
Zürich
Swiss Finance Institute
[2023]
|
| Schlagwörter: | |
| Links: | https://ssrn.com/abstract=4407205 https://doi.org/10.2139/ssrn.4407205 |
| Abstract: | Large language models (LLMs) have significantly transformed the landscape of artificial intelligence by demonstrating their ability to generate human-like text across diverse topics. However, despite their impressive capabilities, LLMs lack recent information and often employ imprecise language, which can be detrimental in domains where accuracy is crucial, such as climate change. In this study, we make use of recent ideas to harness the potential of LLMs by viewing them as agents that access multiple sources, including databases containing recent and precise information about organizations, institutions, and companies. We demonstrate the effectiveness of our method through a prototype agent that retrieves emission data from ClimateWatch (https://www.climatewatchdata.org/) and leverages general Google search. By integrating these resources with LLMs, our approach overcomes the limitations associated with imprecise language and delivers more reliable and accurate information in the critical domain of climate change. This work paves the way for future advancements in LLMs and their application in domains where precision is of paramount importance |
| Beschreibung: | Nach Informationen von SSRN wurde die ursprüngliche Fassung des Dokuments April 1, 2023 erstellt |
| Umfang: | 1 Online-Ressource (7 Seiten) |
| DOI: | 10.2139/ssrn.4407205 |
Internformat
MARC
| LEADER | 00000nam a22000001c 4500 | ||
|---|---|---|---|
| 001 | BV050277390 | ||
| 003 | DE-604 | ||
| 007 | cr|uuu---uuuuu | ||
| 008 | 250513s2023 xx o|||| 00||| eng d | ||
| 024 | 7 | |a 10.2139/ssrn.4407205 |2 doi | |
| 035 | |a (DE-599)KEP096266783 | ||
| 040 | |a DE-604 |b ger |e rda | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-188 | ||
| 100 | 1 | |a Kraus, Mathias |e Verfasser |0 (DE-588)1252711980 |4 aut | |
| 245 | 1 | 0 | |a Enhancing Large Language Models with Climate Resources |
| 264 | 1 | |a Zürich |b Swiss Finance Institute |c [2023] | |
| 300 | |a 1 Online-Ressource (7 Seiten) | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b c |2 rdamedia | ||
| 338 | |b cr |2 rdacarrier | ||
| 500 | |a Nach Informationen von SSRN wurde die ursprüngliche Fassung des Dokuments April 1, 2023 erstellt | ||
| 520 | 3 | |a Large language models (LLMs) have significantly transformed the landscape of artificial intelligence by demonstrating their ability to generate human-like text across diverse topics. However, despite their impressive capabilities, LLMs lack recent information and often employ imprecise language, which can be detrimental in domains where accuracy is crucial, such as climate change. In this study, we make use of recent ideas to harness the potential of LLMs by viewing them as agents that access multiple sources, including databases containing recent and precise information about organizations, institutions, and companies. We demonstrate the effectiveness of our method through a prototype agent that retrieves emission data from ClimateWatch (https://www.climatewatchdata.org/) and leverages general Google search. By integrating these resources with LLMs, our approach overcomes the limitations associated with imprecise language and delivers more reliable and accurate information in the critical domain of climate change. This work paves the way for future advancements in LLMs and their application in domains where precision is of paramount importance | |
| 650 | 0 | 7 | |a Künstliche Intelligenz |0 (DE-588)4033447-8 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Klima |0 (DE-588)4031170-3 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Maschinelles Lernen |0 (DE-588)4193754-5 |2 gnd |9 rswk-swf |
| 653 | |a Large Language Models | ||
| 653 | |a Klimadatenintegration | ||
| 653 | |a KI-Anwendungen im Klimabereich | ||
| 653 | |a KI-Agentenstruktur | ||
| 689 | 0 | 0 | |a Maschinelles Lernen |0 (DE-588)4193754-5 |D s |
| 689 | 0 | 1 | |a Klima |0 (DE-588)4031170-3 |D s |
| 689 | 0 | 2 | |a Künstliche Intelligenz |0 (DE-588)4033447-8 |D s |
| 689 | 0 | |5 DE-604 | |
| 700 | 1 | |a Bingler, Julia Anna |d 1990- |e Verfasser |0 (DE-588)1148306889 |4 aut | |
| 700 | 1 | |a Leippold, Markus |d 1970- |e Verfasser |0 (DE-588)171668367 |4 aut | |
| 700 | 1 | |a Schimanski, Tobias |e Verfasser |4 aut | |
| 700 | 1 | |a Colesanti Senni, Chiara |d 1991- |e Verfasser |0 (DE-588)1208874128 |4 aut | |
| 700 | 1 | |a Stammbach, Dominik |d 1992- |e Verfasser |0 (DE-588)135135440X |4 aut | |
| 700 | 1 | |a Vaghefi, Saeid |e Verfasser |4 aut | |
| 700 | 1 | |a Webersinke, Nicolas |e Verfasser |0 (DE-588)1342213890 |4 aut | |
| 710 | 2 | |a Swiss Finance Institute |e Sonstige |0 (DE-588)10148140-8 |4 oth | |
| 856 | 4 | 0 | |m X:ELVSSRN |u https://ssrn.com/abstract=4407205 |x Verlag |z kostenfrei |
| 856 | 4 | 0 | |m X:ELVSSRN |u https://doi.org/10.2139/ssrn.4407205 |x Resolving-System |z kostenfrei |
| 943 | 1 | |a oai:aleph.bib-bvb.de:BVB01-035611251 | |
Datensatz im Suchindex
| _version_ | 1832014149971869696 |
|---|---|
| adam_text | |
| any_adam_object | |
| author | Kraus, Mathias Bingler, Julia Anna 1990- Leippold, Markus 1970- Schimanski, Tobias Colesanti Senni, Chiara 1991- Stammbach, Dominik 1992- Vaghefi, Saeid Webersinke, Nicolas |
| author_GND | (DE-588)1252711980 (DE-588)1148306889 (DE-588)171668367 (DE-588)1208874128 (DE-588)135135440X (DE-588)1342213890 |
| author_facet | Kraus, Mathias Bingler, Julia Anna 1990- Leippold, Markus 1970- Schimanski, Tobias Colesanti Senni, Chiara 1991- Stammbach, Dominik 1992- Vaghefi, Saeid Webersinke, Nicolas |
| author_role | aut aut aut aut aut aut aut aut |
| author_sort | Kraus, Mathias |
| author_variant | m k mk j a b ja jab m l ml t s ts s c c sc scc d s ds s v sv n w nw |
| building | Verbundindex |
| bvnumber | BV050277390 |
| ctrlnum | (DE-599)KEP096266783 |
| doi_str_mv | 10.2139/ssrn.4407205 |
| format | Electronic eBook |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>00000nam a22000001c 4500</leader><controlfield tag="001">BV050277390</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="007">cr|uuu---uuuuu</controlfield><controlfield tag="008">250513s2023 xx o|||| 00||| eng d</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.2139/ssrn.4407205</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)KEP096266783</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-188</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Kraus, Mathias</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)1252711980</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Enhancing Large Language Models with Climate Resources</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Zürich</subfield><subfield code="b">Swiss Finance Institute</subfield><subfield code="c">[2023]</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">1 Online-Ressource (7 Seiten)</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">Nach Informationen von SSRN wurde die ursprüngliche Fassung des Dokuments April 1, 2023 erstellt</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">Large language models (LLMs) have significantly transformed the landscape of artificial intelligence by demonstrating their ability to generate human-like text across diverse topics. However, despite their impressive capabilities, LLMs lack recent information and often employ imprecise language, which can be detrimental in domains where accuracy is crucial, such as climate change. In this study, we make use of recent ideas to harness the potential of LLMs by viewing them as agents that access multiple sources, including databases containing recent and precise information about organizations, institutions, and companies. We demonstrate the effectiveness of our method through a prototype agent that retrieves emission data from ClimateWatch (https://www.climatewatchdata.org/) and leverages general Google search. By integrating these resources with LLMs, our approach overcomes the limitations associated with imprecise language and delivers more reliable and accurate information in the critical domain of climate change. This work paves the way for future advancements in LLMs and their application in domains where precision is of paramount importance</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Künstliche Intelligenz</subfield><subfield code="0">(DE-588)4033447-8</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Klima</subfield><subfield code="0">(DE-588)4031170-3</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Maschinelles Lernen</subfield><subfield code="0">(DE-588)4193754-5</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="653" ind1=" " ind2=" "><subfield code="a">Large Language Models</subfield></datafield><datafield tag="653" ind1=" " ind2=" "><subfield code="a">Klimadatenintegration</subfield></datafield><datafield tag="653" ind1=" " ind2=" "><subfield code="a">KI-Anwendungen im Klimabereich</subfield></datafield><datafield tag="653" ind1=" " ind2=" "><subfield code="a">KI-Agentenstruktur</subfield></datafield><datafield tag="689" ind1="0" ind2="0"><subfield code="a">Maschinelles Lernen</subfield><subfield code="0">(DE-588)4193754-5</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="1"><subfield code="a">Klima</subfield><subfield code="0">(DE-588)4031170-3</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="2"><subfield code="a">Künstliche Intelligenz</subfield><subfield code="0">(DE-588)4033447-8</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2=" "><subfield code="5">DE-604</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Bingler, Julia Anna</subfield><subfield code="d">1990-</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)1148306889</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Leippold, Markus</subfield><subfield code="d">1970-</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)171668367</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Schimanski, Tobias</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Colesanti Senni, Chiara</subfield><subfield code="d">1991-</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)1208874128</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Stammbach, Dominik</subfield><subfield code="d">1992-</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)135135440X</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Vaghefi, Saeid</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Webersinke, Nicolas</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)1342213890</subfield><subfield code="4">aut</subfield></datafield><datafield tag="710" ind1="2" ind2=" "><subfield code="a">Swiss Finance Institute</subfield><subfield code="e">Sonstige</subfield><subfield code="0">(DE-588)10148140-8</subfield><subfield code="4">oth</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="m">X:ELVSSRN</subfield><subfield code="u">https://ssrn.com/abstract=4407205</subfield><subfield code="x">Verlag</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="m">X:ELVSSRN</subfield><subfield code="u">https://doi.org/10.2139/ssrn.4407205</subfield><subfield code="x">Resolving-System</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="943" ind1="1" ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-035611251</subfield></datafield></record></collection> |
| id | DE-604.BV050277390 |
| illustrated | Not Illustrated |
| indexdate | 2025-05-13T14:00:42Z |
| institution | BVB |
| institution_GND | (DE-588)10148140-8 |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-035611251 |
| open_access_boolean | 1 |
| owner | DE-188 |
| owner_facet | DE-188 |
| physical | 1 Online-Ressource (7 Seiten) |
| publishDate | 2023 |
| publishDateSearch | 2023 |
| publishDateSort | 2023 |
| publisher | Swiss Finance Institute |
| record_format | marc |
| spelling | Kraus, Mathias Verfasser (DE-588)1252711980 aut Enhancing Large Language Models with Climate Resources Zürich Swiss Finance Institute [2023] 1 Online-Ressource (7 Seiten) txt rdacontent c rdamedia cr rdacarrier Nach Informationen von SSRN wurde die ursprüngliche Fassung des Dokuments April 1, 2023 erstellt Large language models (LLMs) have significantly transformed the landscape of artificial intelligence by demonstrating their ability to generate human-like text across diverse topics. However, despite their impressive capabilities, LLMs lack recent information and often employ imprecise language, which can be detrimental in domains where accuracy is crucial, such as climate change. In this study, we make use of recent ideas to harness the potential of LLMs by viewing them as agents that access multiple sources, including databases containing recent and precise information about organizations, institutions, and companies. We demonstrate the effectiveness of our method through a prototype agent that retrieves emission data from ClimateWatch (https://www.climatewatchdata.org/) and leverages general Google search. By integrating these resources with LLMs, our approach overcomes the limitations associated with imprecise language and delivers more reliable and accurate information in the critical domain of climate change. This work paves the way for future advancements in LLMs and their application in domains where precision is of paramount importance Künstliche Intelligenz (DE-588)4033447-8 gnd rswk-swf Klima (DE-588)4031170-3 gnd rswk-swf Maschinelles Lernen (DE-588)4193754-5 gnd rswk-swf Large Language Models Klimadatenintegration KI-Anwendungen im Klimabereich KI-Agentenstruktur Maschinelles Lernen (DE-588)4193754-5 s Klima (DE-588)4031170-3 s Künstliche Intelligenz (DE-588)4033447-8 s DE-604 Bingler, Julia Anna 1990- Verfasser (DE-588)1148306889 aut Leippold, Markus 1970- Verfasser (DE-588)171668367 aut Schimanski, Tobias Verfasser aut Colesanti Senni, Chiara 1991- Verfasser (DE-588)1208874128 aut Stammbach, Dominik 1992- Verfasser (DE-588)135135440X aut Vaghefi, Saeid Verfasser aut Webersinke, Nicolas Verfasser (DE-588)1342213890 aut Swiss Finance Institute Sonstige (DE-588)10148140-8 oth X:ELVSSRN https://ssrn.com/abstract=4407205 Verlag kostenfrei X:ELVSSRN https://doi.org/10.2139/ssrn.4407205 Resolving-System kostenfrei |
| spellingShingle | Kraus, Mathias Bingler, Julia Anna 1990- Leippold, Markus 1970- Schimanski, Tobias Colesanti Senni, Chiara 1991- Stammbach, Dominik 1992- Vaghefi, Saeid Webersinke, Nicolas Enhancing Large Language Models with Climate Resources Künstliche Intelligenz (DE-588)4033447-8 gnd Klima (DE-588)4031170-3 gnd Maschinelles Lernen (DE-588)4193754-5 gnd |
| subject_GND | (DE-588)4033447-8 (DE-588)4031170-3 (DE-588)4193754-5 |
| title | Enhancing Large Language Models with Climate Resources |
| title_auth | Enhancing Large Language Models with Climate Resources |
| title_exact_search | Enhancing Large Language Models with Climate Resources |
| title_full | Enhancing Large Language Models with Climate Resources |
| title_fullStr | Enhancing Large Language Models with Climate Resources |
| title_full_unstemmed | Enhancing Large Language Models with Climate Resources |
| title_short | Enhancing Large Language Models with Climate Resources |
| title_sort | enhancing large language models with climate resources |
| topic | Künstliche Intelligenz (DE-588)4033447-8 gnd Klima (DE-588)4031170-3 gnd Maschinelles Lernen (DE-588)4193754-5 gnd |
| topic_facet | Künstliche Intelligenz Klima Maschinelles Lernen |
| url | https://ssrn.com/abstract=4407205 https://doi.org/10.2139/ssrn.4407205 |
| work_keys_str_mv | AT krausmathias enhancinglargelanguagemodelswithclimateresources AT binglerjuliaanna enhancinglargelanguagemodelswithclimateresources AT leippoldmarkus enhancinglargelanguagemodelswithclimateresources AT schimanskitobias enhancinglargelanguagemodelswithclimateresources AT colesantisennichiara enhancinglargelanguagemodelswithclimateresources AT stammbachdominik enhancinglargelanguagemodelswithclimateresources AT vaghefisaeid enhancinglargelanguagemodelswithclimateresources AT webersinkenicolas enhancinglargelanguagemodelswithclimateresources AT swissfinanceinstitute enhancinglargelanguagemodelswithclimateresources |