langtest.utils.custom_types.helpers.llm_prompt_eval#

llm_prompt_eval(eval_model, dataset_name: str, inputs: List[dict], predictions: List[dict]) → bool#

Evaluates model predictions using the Language Model Metric (LLM) with prompt-based evaluation.

Parameters:

• eval_model – Language model for evaluation.

• dataset_name (str) – Name of the dataset being evaluated.

• inputs (List[dict]) – List of input dictionaries.

• predictions (List[dict]) – List of prediction dictionaries.

Returns:

True if the model’s prediction passes the LLM evaluation, False otherwise.

Return type:

bool