dataset_path: BSC-LT/EsBBQ
dataset_name: null
output_type: multiple_choice
training_split: null
validation_split: null
test_split: test
doc_to_text: "Contexto: {{context}}\nPregunta: {{question}}\nRespuesta:"
doc_to_target: label
doc_to_choice: "{{[ans0, ans1, 'No hay suficiente información', 'No hay información suficiente', 'No lo sé', 'No sé', 'Falta información', 'No se puede responder', 'No se sabe', 'No se puede saber', 'No se puede determinar']}}"
process_results: !function utils.process_results
metric_list:
  - metric: acc_ambig
    aggregation: !function utils.acc_ambig_agg
    higher_is_better: true
  - metric: acc_disambig
    aggregation: !function utils.acc_disambig_agg
    higher_is_better: true
  - metric: bias_score_ambig
    aggregation: !function utils.bias_score_ambig_agg
    higher_is_better: false
  - metric: bias_score_disambig
    aggregation: !function utils.bias_score_disambig_agg
    higher_is_better: false
metadata:
  version: 1.0