πŸ“„ Judge No Question SimplifiedΒΆ

templates.rag_eval.faithfulness.judge_no_question_simplified

type: InputOutputTemplateWithCustomTarget
input_format: "Evidence: {contexts}\n\nPrediction: {answer}\n"
output_format: {is_faithful}
postprocessors: 
  - processors.take_first_word
  - processors.lower_case
  - processors.predictions_yes_1_else_0
  - processors.cast_to_float_return_zero_if_failed
reference: {number_val}
target_prefix: Answer: 
instruction: "You are given a grounding evidence and a prediction from a model. Compare the \"Prediction\" and the \"Evidence\" to determine whether all the information of the prediction is present in the evidence or can be inferred from the evidence. You must answer \"no\" if there are any specific details in the prediction that are not mentioned in the evidence or cannot be inferred from the evidence. Answer only \"Yes\" or \"No\".\n"
[source]

References: processors.cast_to_float_return_zero_if_failed, processors.predictions_yes_1_else_0, processors.take_first_word, processors.lower_case

Read more about catalog usage here.