ClimaQA_SLO - Slovenian Climate Question-Answering Benchmark
Fuente:
Zenodo
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Recurso digital |
| Sprache: | Slowenisch |
| Veröffentlicht: |
Zenodo
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866901849822461952 |
|---|---|
| author | Ferk Ovčjak, Monika Strnad, Damjan Kožuh, Ines |
| author_facet | Ferk Ovčjak, Monika Strnad, Damjan Kožuh, Ines |
| contents | <p><span lang="EN-GB">Slovenian Climate Question-Answering Benchmark (ClimaQA_SLO) for fact-checking LLMs with domain-specific knowledge related to Slovenian topics connected to the environment such as climate change, energy, and forestry.</span></p> <p><span lang="EN-GB"><strong>Tested LLMs: </strong>GPT-4o, GPT-4o_WEB, GPT-3.5-turbo, GPT-o3, GPT-o3_WEB<br></span></p> <p><span lang="EN-GB"><strong>Metrics: </strong>accuracy, F score (SimpleQA-based)</span></p> <p><span lang="EN-GB"><strong>Language: </strong>Slovenian</span></p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_15862255 |
| institution | Zenodo |
| language | slv |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | ClimaQA_SLO - Slovenian Climate Question-Answering Benchmark Ferk Ovčjak, Monika Strnad, Damjan Kožuh, Ines Large language models Fact checking Local knowledge Environment <p><span lang="EN-GB">Slovenian Climate Question-Answering Benchmark (ClimaQA_SLO) for fact-checking LLMs with domain-specific knowledge related to Slovenian topics connected to the environment such as climate change, energy, and forestry.</span></p> <p><span lang="EN-GB"><strong>Tested LLMs: </strong>GPT-4o, GPT-4o_WEB, GPT-3.5-turbo, GPT-o3, GPT-o3_WEB<br></span></p> <p><span lang="EN-GB"><strong>Metrics: </strong>accuracy, F score (SimpleQA-based)</span></p> <p><span lang="EN-GB"><strong>Language: </strong>Slovenian</span></p> |
| title | ClimaQA_SLO - Slovenian Climate Question-Answering Benchmark |
| topic | Large language models Fact checking Local knowledge Environment |
| url | https://doi.org/10.5281/zenodo.15862255 |