📄 Judge Answer Relevance Verbal Good Bad¶

templates.rag_eval.answer_relevance.judge_answer_relevance_verbal_good_bad

type: InputOutputTemplateWithCustomTarget
input_format: "Question: {question}\n\nPrediction: {answer}\n"
output_format: {is_relevant}
postprocessors: 
  - processors.extract_from_double_brackets
  - processors.extract_verbal_judgement_bad_good
  - processors.cast_to_float_return_zero_if_failed
reference: {number_val}
target_prefix: Answer: 
instruction: "You are given a question and a prediction from a model. Please determine to what extent, on a scale of 0 to 10, the prediction answers the question.\nReply with your rating score without any preceding explanation.\n"
[source]

References: processors.cast_to_float_return_zero_if_failed, processors.extract_verbal_judgement_bad_good, processors.extract_from_double_brackets