table

Author: lgayhardt

articles/ai-studio/concepts/evaluation-metrics-built-in.md

@@ -48,7 +48,7 @@ Another consideration for evaluators is whether they're AI-assisted (using model
 - Generation quality evaluators
     These evaluators focus on various scenarios for quality measurement.
 
-| Recommended scenario | Evaluator Type | Why use this evaluator? | Evaluators |
+    | Recommended scenario | Evaluator Type | Why use this evaluator? | Evaluators |
     |---|---|---|---|
     | Retrieval-augmented generation question and answering (RAG QA), summarization, or information retrieval | AI-assisted (using language model as a judge) | Groundedness, retrieval, and relevance metrics form a "RAG triad" that examines the quality of responses and retrieved context chunks | *Groundedness* </br> Measures how well the generated response aligns with the given context, focusing on its relevance and accuracy with respect to the context. <br></br> *Groundedness Pro* </br> Detects whether the generated text response is consistent or accurate with respect to the given context. <br></br> *Retrieval* </br> Measures the quality of search without ground truth. It focuses on how relevant the context chunks (encoded as a string) are to address a query and how the most relevant context chunks are surfaced at the top of the list. <br></br> *Relevance* </br> Measures how effectively a response addresses a query. It assesses the accuracy, completeness, and direct relevance of the response based solely on the given query. <br></br>  |
     | Generative business writing such as summarizing meeting notes, creating marketing materials, and drafting emails | AI-assisted (using language model as a judge) | Examines the logical and linguistic quality of responses | *Coherence* </br> Measures the logical and orderly presentation of ideas in a response, allowing the reader to easily follow and understand the writer's train of thought. <br></br> *Fluency* </br>  Measures the effectiveness and clarity of written communication, focusing on grammatical accuracy, vocabulary range, sentence complexity, coherence, and overall readability. |