Assesses whether a response is firmly based on the provided context. This evaluation ensures that the response does not introduce information that is not supported by the context, thereby maintaining factual accuracy and relevance.
output
is well-grounded in the input
.output
includes information not present in or supported by the input
.Click here to learn how to setup evaluation using SDK.
Input Type | Parameter | Type | Description |
---|---|---|---|
Required Inputs | output | string | The generated response from the model. |
input | string | The user-provided input to the model (acting as the source context). |
Output | Type | Description |
---|---|---|
Score | float | Returns a score between 0 and 1, where higher values indicate better grounding in the input. |