Factual consistency checking in Prompt Engineering / GenAI - Model Metrics & Evaluation

Metrics & Evaluation - Factual consistency checking

Which metric matters for Factual consistency checking and WHY

Factual consistency checking means making sure the AI's answers are true and match real facts. The key metrics here are Precision and Recall. Precision tells us how many of the AI's claims are actually correct. Recall tells us how many true facts the AI managed to include without missing them. We want both high because we want the AI to say only true facts (high precision) and not miss important facts (high recall).

Confusion matrix for Factual consistency checking

      | Predicted True | Predicted False |
      |----------------|-----------------|
      | True Positive  | False Negative  |
      | (Correct fact) | (Missed fact)   |
      |----------------|-----------------|
      | False Positive | True Negative   |
      | (Wrong fact)   | (Correctly no fact) |
    

Example numbers for 100 claims:

      TP = 70 (correct facts found)
      FP = 10 (wrong facts stated)
      FN = 15 (true facts missed)
      TN = 5  (correctly no false claims)
    

Precision vs Recall tradeoff with examples

If the AI is very careful and only states facts it is sure about, it will have high precision but might miss some facts, so lower recall. This means fewer wrong facts but some true facts are missing.

If the AI tries to include every possible fact, it will have high recall but might include wrong facts, so lower precision. This means more complete answers but some errors.

For example, a medical AI should have high precision to avoid wrong advice. A news summarizer might want higher recall to cover all important facts.

What good vs bad metric values look like

Good: Precision and recall both above 0.85 means most facts are correct and most true facts are included.

Bad: Precision below 0.5 means many wrong facts. Recall below 0.5 means many true facts missed. Either case means the AI is not reliable.

Common pitfalls in factual consistency metrics

• Accuracy paradox: High overall accuracy can hide poor precision or recall if data is unbalanced.
• Data leakage: If test facts appear in training, metrics look better but model is not truly consistent.
• Overfitting: Model memorizes facts but fails on new facts, causing low recall.
• Ignoring context: Some facts depend on context; metrics must consider this to avoid false errors.

Self-check question

Your model has 98% accuracy but only 12% recall on true facts. Is it good for production?

Answer: No. The model misses most true facts (low recall), so it is not reliable even if accuracy looks high. It needs improvement to find more true facts.

Key Result

Precision and recall are key to measure how many AI facts are correct and how many true facts are found.

Practice

1. What is the main purpose of factual consistency checking in AI-generated text?

easy

A. To reduce the size of the AI model

B. To improve the speed of AI text generation

C. To make AI text more creative and imaginative

D. To ensure the AI's output matches true and reliable information

Solution

1. Step 1: Understand the goal of factual consistency checking

   It is used to verify that AI-generated text is accurate and trustworthy.

2. Step 2: Compare options with this goal

   Only To ensure the AI's output matches true and reliable information talks about matching output with true information, which fits the goal.

3. Final Answer:

   To ensure the AI's output matches true and reliable information -> Option D

4. Quick Check:

   Purpose = Verify truthfulness [OK]

Hint: Check which option talks about truth and reliability [OK]

Common Mistakes:

• Confusing creativity with factual accuracy
• Thinking speed or size relates to factual checking
• Ignoring the need for truth in AI outputs

2. Which of the following is a correct simple method for factual consistency checking?

easy

A. Using word overlap between generated text and reference text

B. Training a new AI model from scratch

C. Increasing the number of layers in the AI model

D. Reducing the vocabulary size of the AI

Solution

1. Step 1: Identify simple factual checking methods

   Simple methods often compare words between generated and trusted texts.

2. Step 2: Match options to this method

   Using word overlap between generated text and reference text describes word overlap, a known simple method. Others relate to model design, not checking.

3. Final Answer:

   Using word overlap between generated text and reference text -> Option A

4. Quick Check:

   Simple method = Word overlap [OK]

Hint: Look for word comparison methods, not model changes [OK]

Common Mistakes:

• Confusing model training with checking methods
• Choosing options about model size or layers
• Ignoring the comparison aspect of checking

3. Given the generated sentence: 'The Eiffel Tower is in Berlin.' and the reference sentence: 'The Eiffel Tower is in Paris.', which factual consistency check result is correct?

medium

A. The sentences are factually consistent because they share many words.

B. The sentences are inconsistent because they have different lengths.

C. The sentences are factually inconsistent because the location is different.

D. The sentences are consistent because both mention the Eiffel Tower.

Solution

1. Step 1: Compare key facts in both sentences

   Both mention Eiffel Tower, but locations differ: Berlin vs Paris.

2. Step 2: Determine factual consistency

   Different locations mean factual inconsistency despite word overlap.

3. Final Answer:

   The sentences are factually inconsistent because the location is different. -> Option C

4. Quick Check:

   Location mismatch = Inconsistent [OK]

Hint: Focus on key fact differences, not just shared words [OK]

Common Mistakes:

• Assuming word overlap means consistency
• Ignoring critical fact differences
• Confusing sentence length with factual accuracy

4. You have a simple factual consistency checker that counts overlapping words. It incorrectly marks 'The capital of France is Paris.' and 'Paris is the capital of France.' as inconsistent. What is the likely error?

medium

A. The checker does not ignore word order, causing false inconsistency

B. The checker uses AI understanding, which is too strict

C. The checker compares sentence lengths only

D. The checker ignores common words like 'the' and 'is'

Solution

1. Step 1: Analyze the checker behavior

   It counts overlapping words but marks reordered sentences inconsistent.

2. Step 2: Identify the cause

   Not ignoring word order causes false negatives despite same words.

3. Final Answer:

   The checker does not ignore word order, causing false inconsistency -> Option A

4. Quick Check:

   Word order sensitivity = False inconsistency [OK]

Hint: Check if word order affects overlap counting [OK]

Common Mistakes:

• Assuming AI understanding causes error here
• Thinking sentence length matters
• Ignoring the role of stop words

5. You want to improve factual consistency checking by combining word overlap with AI understanding. Which approach best achieves this?

hard

A. Only count exact word matches without context

B. Use a model that compares semantic meaning, then verify key facts match

C. Ignore reference text and trust AI output blindly

D. Reduce the AI model size to speed up checking

Solution

1. Step 1: Understand combining methods

   Combining word overlap with AI understanding means checking meaning and facts.

2. Step 2: Evaluate options

   Use a model that compares semantic meaning, then verify key facts match uses semantic comparison and fact verification, best for improved checking.

3. Final Answer:

   Use a model that compares semantic meaning, then verify key facts match -> Option B

4. Quick Check:

   Semantic + fact check = Best approach [OK]

Hint: Pick option combining meaning and fact verification [OK]

Common Mistakes:

• Choosing only word matching without context
• Ignoring reference text
• Focusing on model size instead of accuracy