An 857-item BIG-bench 10-way task that asks which English discourse marker continues a sentence pair, drawn from Discovery.
unassessed
| Category | knowledge |
|---|---|
| Subcategory | BIG-bench 10-way discourse connective prediction (857 items) |
| Page status | unknown |
| Metric | multiple_choice_grade |
| Direction | higher_is_better |
| Unit | % |
| Dataset size | 857 |
| Dataset licence | Apache-2.0 |
| Publisher | Google (BIG-bench collaboration) |
discourse_marker_prediction gives one English sentence and ten candidate continuations that differ mainly in the opening discourse marker. The model must pick the continuation whose marker is the original connective. Author Damien Sileo filtered Discovery test pairs so a supervised RoBERTa was both correct and at least 10% more confident than the runner-up, then sampled about five such items per marker. The skill is rare connective choice, not PDTB implicit-relation labelling. It is not [bbh](bbh.md).
Ten-option multiple choice with preferred metric multiple_choice_grade. append_choices_to_input is true. Keywords include zero-shot, one-shot and many-shot. Canary GUID embedded.
No model card in ModelSpec reports this benchmark yet.