Multimodal RAG in Prompt Engineering / GenAI - Model Metrics & Evaluation

Metrics & Evaluation - Multimodal RAG

Which metric matters for Multimodal RAG and WHY

Multimodal RAG (Retrieval-Augmented Generation) combines text and images or other data types to answer questions or generate content. The key metrics are Recall and F1 score. Recall is important because the model must find the right information from many sources. F1 balances recall with precision, showing how accurate and complete the answers are. For generation quality, BLEU or ROUGE scores help measure how close the output is to good answers.

Confusion Matrix for Multimodal RAG (Example)

      | Predicted Relevant | Predicted Irrelevant |
      |--------------------|----------------------|
      | True Positive (TP): 80  | False Negative (FN): 20 |
      | False Positive (FP): 15 | True Negative (TN): 85 |

      Total samples = 80 + 20 + 15 + 85 = 200

      Precision = TP / (TP + FP) = 80 / (80 + 15) = 0.842
      Recall = TP / (TP + FN) = 80 / (80 + 20) = 0.8
      F1 Score = 2 * (Precision * Recall) / (Precision + Recall) ≈ 0.82
    

Precision vs Recall Tradeoff with Examples

In Multimodal RAG, high recall means the model finds most relevant info, which is good for thorough answers. But this can lower precision, causing some wrong info to appear.

Example 1: A medical assistant using RAG must have high recall to not miss any important symptoms, even if some extra info is included.

Example 2: A customer support bot should have high precision to avoid giving wrong answers, even if it misses some less common questions.

What Good vs Bad Metric Values Look Like

Good: Precision and recall both above 0.8, F1 score near 0.8 or higher, BLEU/ROUGE scores showing close match to expected answers.

Bad: Precision or recall below 0.5, meaning many wrong or missed answers. Low F1 score below 0.6 shows imbalance. BLEU/ROUGE scores near zero mean poor generation quality.

Common Metrics Pitfalls

• Accuracy paradox: High accuracy can be misleading if data is imbalanced (e.g., many irrelevant items).
• Data leakage: If retrieval uses future info, metrics look better but model fails in real use.
• Overfitting: Very high training scores but low test scores mean model memorizes data, not generalizes.
• Ignoring multimodal balance: Metrics only on text or images separately miss how well the model combines both.

Self-Check Question

Your Multimodal RAG model has 98% accuracy but only 12% recall on relevant info. Is it good for production? Why or why not?

Answer: No, it is not good. The very low recall means the model misses most relevant information, which is critical for retrieval tasks. High accuracy here is misleading because most data is irrelevant, so the model guesses irrelevant too often. You need to improve recall to ensure the model finds the right info.

Key Result

Recall and F1 score are key to measure how well Multimodal RAG finds and balances relevant information across data types.

Practice

1. What is the main purpose of Multimodal RAG in AI systems?

easy

A. To generate images from text descriptions without retrieval

B. To translate languages using only text data

C. To combine text and images for better information retrieval and generation

D. To classify images into categories without text input

Solution

1. Step 1: Understand the components of Multimodal RAG

   Multimodal RAG uses both text and image data to improve retrieval and generation tasks.

2. Step 2: Identify the main goal

   The goal is to combine these data types to find and generate better answers than using text or images alone.

3. Final Answer:

   To combine text and images for better information retrieval and generation -> Option C

4. Quick Check:

   Multimodal RAG = combine text + images [OK]

Hint: Remember: Multimodal means multiple data types combined [OK]

Common Mistakes:

• Thinking it only works with text
• Confusing it with image-only models
• Assuming it only generates images

2. Which of the following is the correct component setup for a Multimodal RAG system?

easy

A. Single encoder for both text and images, no retriever

B. Separate encoders for text and images, plus a retriever and a generator

C. Only a text encoder and a generator, no image processing

D. Only an image encoder and a retriever, no text input

Solution

1. Step 1: Recall the architecture of Multimodal RAG

   It uses separate encoders for text and images to handle each data type properly.

2. Step 2: Understand the role of retriever and generator

   The retriever finds relevant data, and the generator creates the final output combining both modalities.

3. Final Answer:

   Separate encoders for text and images, plus a retriever and a generator -> Option B

4. Quick Check:

   Separate encoders + retriever + generator = B [OK]

Hint: Look for separate encoders and both retriever and generator [OK]

Common Mistakes:

• Assuming one encoder handles both text and images
• Ignoring the retriever component
• Thinking image processing is optional

3. Given the following pseudocode for a Multimodal RAG retrieval step, what will be the output type?

text_embedding = text_encoder(text_input)
image_embedding = image_encoder(image_input)
combined_embedding = concatenate(text_embedding, image_embedding)
retrieved_docs = retriever.retrieve(combined_embedding)
print(type(retrieved_docs))

medium

A. <class 'int'>

B. <class 'dict'>

C. <class 'str'>

D. <class 'list'>

Solution

1. Step 1: Understand the retriever output

   The retriever typically returns a list of documents or data items relevant to the query embedding.

2. Step 2: Identify the output type printed

   Since retrieved_docs holds multiple documents, its type is a list.

3. Final Answer:

   <class 'list'> -> Option D

4. Quick Check:

   Retriever output = list of documents [OK]

Hint: Retriever returns a list of relevant documents [OK]

Common Mistakes:

• Assuming output is a string or dictionary
• Confusing embedding types with retrieval output
• Expecting a single document instead of a list

4. You have this code snippet for a Multimodal RAG generator:

def generate_answer(text, image):
    text_emb = text_encoder(text)
    image_emb = image_encoder(image)
    combined = text_emb + image_emb
    docs = retriever.retrieve(combined)
    answer = generator.generate(docs)
    return answer

What is the main error in this code?

medium

A. Using '+' to combine embeddings instead of concatenation

B. Missing image encoder call

C. Retriever should not be called before generator

D. Generator cannot take documents as input

Solution

1. Step 1: Check how embeddings are combined

   Embeddings from different modalities should be concatenated, not added, to preserve information.

2. Step 2: Understand the impact of using '+' operator

   Adding embeddings sums values element-wise, which can lose modality-specific features.

3. Final Answer:

   Using '+' to combine embeddings instead of concatenation -> Option A

4. Quick Check:

   Combine embeddings = concatenate, not add [OK]

Hint: Use concatenate, not plus, to combine embeddings [OK]

Common Mistakes:

• Thinking '+' merges embeddings correctly
• Ignoring the need for separate encoders
• Assuming retriever or generator order is wrong

5. You want to improve a Multimodal RAG system that sometimes misses relevant images when answering questions. Which approach is best to fix this?

hard

A. Train the image encoder with more diverse image-text pairs to improve embedding quality

B. Remove the retriever and rely only on the generator

C. Use only text data and ignore images to simplify the model

D. Replace the text encoder with a simpler model to speed up processing

Solution

1. Step 1: Identify the cause of missing relevant images

   Low-quality image embeddings can cause the retriever to miss relevant images.

2. Step 2: Choose the best fix

   Training the image encoder with more diverse data improves embedding quality and retrieval accuracy.

3. Final Answer:

   Train the image encoder with more diverse image-text pairs to improve embedding quality -> Option A

4. Quick Check:

   Better image encoder training = better retrieval [OK]

Hint: Improve encoder training with diverse data for better retrieval [OK]

Common Mistakes:

• Removing retriever loses retrieval benefits
• Ignoring images reduces multimodal power
• Simplifying text encoder won't fix image retrieval