Corrections on required field specification for faithfulness and corr…

…ectness

website/docs/autoeval/metrics.mdx

@@ -18,7 +18,7 @@ All evaluators work on some combination of the following properties:
 - `output`: The response generated by the application (e.g. LLM generation)
 - `ground_truth`: Factual data, either the ideal correct response, or context used to generate the output (e.g. data retrieved from a vector DB)
 
-Running evals is possible both from the [Model Console](https://lastmileai.dev/models) dashboard as well as the [API](/sdk).
+Running evals is possible both from the [Model Console](https://lastmileai.dev/models) dashboard as well as the [API/SDKs](/sdk).
 
 You can run a one-off evaluation from the model playground. Open any metric in the [Model Console](https://lastmileai.dev/models),
 and click `Run Model` (the play button) to compute a score on some provided data.
@@ -38,7 +38,7 @@ The task is a Natural Language Inference (NLI) task that measures if the output
 Required fields:
 - `input` - e.g. user query
 - `output` - LLM response
-- `ground_truth` - ideal response, or context used to generate output.
+- `ground_truth` - context used to generate output
 
 :::tip
 The LastMile faithfulness evaluator is able to identify subtle mistakes that an LLM might make.
@@ -358,7 +358,7 @@ It returns a 0->1 score which answers: _"Does the LLM-generated response correct
 Required fields:
 - `input` - Input prompt
 - `output` - LLM response
-- `ground_truth` - context used to generate output.
+- `ground_truth` - Ideal response or correct answer
 
 #### Usage Guide
 
@@ -650,4 +650,4 @@ console.table(evalResult);
 
 :::info
 Don't see a metric that perfectly fits your use case? [Design your own](/autoeval/fine-tune) with the fine-tuning service, or [get in touch](https://discord.com/invite/xBhNKTetGx)!
-:::
+:::