tag:
  - acp_mcq_cot_2shot
  - acp_bench
output_type: generate_until
dataset_path: ibm-research/acp_bench
test_split: test
num_fewshot: 2
doc_to_target: "{{answer}}"
doc_to_text: "**Question**: {{context}}  {{question}} **Thoughts**:"
generation_kwargs:
  until:
    - "\n\n\n\n"
    - "**Question**:"
    - "**Question:**"
    - "Q:"
  do_sample: false
  temperature: 0.0
  max_gen_toks: 1024
metric_list:
  - metric: exact_match
    ignore_case: true
    ignore_punctuation: true
    regexes_to_ignore:
      - "\\.$"
      - ","
      - "\\\\"
      - "\n"
      - '"'
filter_list:
  - name: "mcq-extract"
    filter:
      - function: multi_choice_regex
        group_select: -1
        ignore_case: true
        ignore_punctuation: true
        regex_pattern: '(((?<=[answer is ])[A-D])|([A-D]\n)|([A-D]\.)|( [A-D] )|(^[A-D]$)|(\[[A-D]\])|([A-D])|(?<=..Final Answer..: )(.*)(?=.)|(?<=..answer..: )(.*)(?=.)|(?<=..Answer..: )(.*)(?=.))'
      - function: "take_first"
metadata:
  version: 1.0
