group: - multiple_choice task: qa4mre_2012 dataset_path: qa4mre dataset_name: 2012.main.EN output_type: multiple_choice test_split: train template_aliases: "{% set answer_choices = answer_options['answer_str'] %}" doc_to_text: "{{document_str.strip()}}\nQuestion: {{question_str}}\nChoices:\n- {{answer_choices|join('\n- ')}}\nAnswer:" doc_to_target: !function preprocess_qa4mre.doc_to_target gold_alias: !function preprocess_qa4mre.qa4mre_process should_decontaminate: true doc_to_decontamination_query: "{{document_str.strip()}} + ' ' + {{question_str}}" metric_list: - metric: acc aggregation: mean higher_is_better: true - metric: acc_norm aggregation: mean higher_is_better: true