BIG-bench two-choice task: match a ~500-word Gutenberg passage to its author, in same-genre and genre-swapped pairings.
unassessed
| Category | reasoning |
|---|---|
| Subcategory | style-based same-author identification with genre swap |
| Page status | unknown |
| Metric | multiple_choice_grade |
| Direction | higher_is_better |
| Unit | % |
| Dataset size | 880 |
| Dataset licence | Apache-2.0 |
| Publisher | Google (BIG-bench collaboration); task authors at HU Berlin, Uni Weimar, Uni Halle, Uni Leipzig |
The model sees one reference passage of about 500 words and two candidate passages of similar length. It must pick the candidate written by the same author as the reference. One subtask keeps genre aligned (adult vs children's literature). The swapped subtask pairs same-author texts across genre and same-genre texts across authors, so topic cues point the wrong way.
Two-option multiple choice. Preferred metric multiple_choice_grade. Dummy-model header counts 880 queries. Canary GUID embedded.
No model card in ModelSpec reports this benchmark yet.