diff --git a/src/metacoder/evals/runner.py b/src/metacoder/evals/runner.py index 67a9619..d7bbf7d 100644 --- a/src/metacoder/evals/runner.py +++ b/src/metacoder/evals/runner.py @@ -64,8 +64,6 @@ def get_default_metrics() -> Dict[str, BaseMetric]: return { "CorrectnessMetric": GEval( name="Correctness", - criteria="Determine whether the actual output is factually correct based on the expected output.", - # NOTE: you can only provide either criteria or evaluation_steps, and not both evaluation_steps=[ "Check whether the facts in 'actual output' contradicts any facts in 'expected output'", "You should also heavily penalize omission of detail",