dataset_path: HAERAE-HUB/HAE_RAE_BENCH
test_split: test
fewshot_split: test
output_type: multiple_choice
doc_to_text: "{{query}}"
doc_to_choice: ["(A)", "(B)", "(C)", "(D)", "(E)"]
doc_to_target: "{{answer}}"
metric_list:
  - metric: acc
    aggregation: mean
    higher_is_better: true
  - metric: acc_norm
    aggregation: mean
    higher_is_better: true
metadata:
  version: 1.0