📄 Email Effectiveness¶

metrics.llm_as_judge.direct.criteria.email_effectiveness

CriteriaWithOptions(
    name="email_effectiveness",
    description="Does the email response effectively communicate the desired message?",
    prediction_field="email response",
    context_fields=[],
    options=[
        CriteriaOption(
            name="Excellent",
            description="The email response clearly and effectively communicates the desired message with no ambiguity.",
        ),
        CriteriaOption(
            name="Acceptable",
            description="The email response communicates the desired message but may have minor ambiguities or areas for improvement.",
        ),
        CriteriaOption(
            name="Could be Improved",
            description="The email response struggles to communicate the desired message, leading to confusion or misunderstanding.",
        ),
        CriteriaOption(
            name="Bad",
            description="The email response fails to communicate the desired message effectively.",
        ),
    ],
    option_map={
        "Excellent": 1.0,
        "Acceptable": 0.5,
        "Could be Improved": 0.25,
        "Bad": 0.0,
    },
)

[source]

from unitxt.llm_as_judge_constants import CriteriaOption

Explanation about CriteriaWithOptions¶

Criteria used by DirectLLMJudge to run evaluations.

Explanation about CriteriaOption¶

A criteria option.