Statements (14)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:performance
|
| gptkbp:dataSource |
parliamentary records
|
| gptkbp:field |
gptkb:artificial_intelligence
natural language processing |
| gptkbp:focus |
parliamentary question answering
|
| gptkbp:introducedIn |
2023
|
| gptkbp:purpose |
evaluate large language models
|
| gptkbp:relatedTo |
government transparency
LLM evaluation |
| gptkbp:usedBy |
gptkb:researchers
|
| gptkbp:usedFor |
measuring LLM performance on parliamentary data
|
| gptkbp:bfsParent |
gptkb:Gender_Shades_study
|
| gptkbp:bfsLayer |
7
|
| https://www.w3.org/2000/01/rdf-schema#label |
Pilot Parliaments Benchmark
|