pyrit.score.LikertScaleEvalFiles

pyrit.score.LikertScaleEvalFiles#

class LikertScaleEvalFiles(human_labeled_datasets_files: List[str], result_file: str, harm_category: str | None = None)[source]#

Bases: object

Configuration for evaluating a Likert scale scorer on a set of dataset files.

Parameters:

  • human_labeled_datasets_files (List[str]) – List of glob patterns to match CSV files.

  • result_file (str) – Name of the result file for storing evaluation results.

  • harm_category (Optional[str]) – The harm category for harm scorers. Defaults to None. The harm definition path is derived as “{harm_category}.yaml”.

__init__(human_labeled_datasets_files: List[str], result_file: str, harm_category: str | None = None) → None#

Methods

__init__(human_labeled_datasets_files, ...)

Attributes

harm_category

human_labeled_datasets_files

result_file

harm_category: str | None = None#
human_labeled_datasets_files: List[str]#
result_file: str#
Contents