This evaluation template checks whether a text contains unnecessary apologies or excessively apologetic language. It helps ensure AI responses maintain an appropriately confident and professional tone without defaulting to overly apologetic phrasing.

Evaluation Using SDK

result = evaluator.evaluate(
    eval_templates="no_apologies",
    inputs={
        "input": "Dear Sir, I hope this email finds you well. I look forward to any insights or advice you might have whenever you have a free moment"
    },
    model_name="turing_flash"
)

print(result.eval_results[0].output)
print(result.eval_results[0].reason)

Troubleshooting

If you encounter issues with this evaluation:
  • This evaluation looks for explicit apologies (“sorry,” “apologize,” etc.) as well as excessively deferential language
  • Some contexts legitimately require apologies - this evaluation is best used when checking for unnecessary apologetic language
  • The evaluation may not catch subtle or implicit forms of apologetic language
  • Consider cultural context, as norms around apologies vary globally
  • is-polite: Ensures communication remains respectful even without apologies
  • tone: Provides broader assessment of communication style and confidence
  • cultural-sensitivity: Evaluates awareness of and respect for diverse cultural norms around apologies