Why LLMs understand and generate text in Prompt Engineering / GenAI - Why Metrics Matter

Metrics & Evaluation - Why LLMs understand and generate text

Which metric matters for this concept and WHY

For large language models (LLMs) that understand and generate text, the key metrics are perplexity and accuracy on language tasks. Perplexity measures how well the model predicts the next word in a sentence. Lower perplexity means the model better understands language patterns. Accuracy on tasks like question answering or text classification shows how well the model generates meaningful and correct text. These metrics matter because they tell us if the model truly grasps language structure and meaning.

Confusion matrix or equivalent visualization (ASCII)

For text generation, a confusion matrix is less common, but for classification tasks done by LLMs, it looks like this:

      | Predicted Positive | Predicted Negative
    -------------------------------------------
    Actual Positive |       TP = 80       |       FN = 20
    Actual Negative |       FP = 10       |       TN = 90
    

This helps calculate precision and recall, showing how well the model distinguishes correct from incorrect answers.

Precision vs Recall tradeoff with concrete examples

When LLMs generate text, sometimes they must balance precision (being correct) and recall (covering all relevant info). For example, in a chatbot answering questions, high precision means answers are accurate and trustworthy. High recall means the model tries to cover all possible correct answers, even if some are less precise. If the model is too cautious (high precision, low recall), it may miss useful info. If it tries to say everything (high recall, low precision), it may give wrong or confusing answers.

What "good" vs "bad" metric values look like for this use case

A good LLM has low perplexity (e.g., below 20 on standard datasets) and high accuracy (above 85%) on language tasks. This means it predicts words well and generates meaningful text. A bad model has high perplexity (above 50) and low accuracy (below 60%), showing poor understanding and confusing output. For classification tasks, good precision and recall are both above 80%. If one is very low, the model either misses important info or makes many mistakes.

Metrics pitfalls (accuracy paradox, data leakage, overfitting indicators)

One pitfall is the accuracy paradox: a model might have high accuracy by guessing common words but fail to understand rare or complex language. Data leakage happens if the model sees test examples during training, inflating metrics falsely. Overfitting means the model performs well on training data but poorly on new text, showing low generalization. Monitoring perplexity on unseen data helps detect this.

Self-check question

Your LLM has 98% accuracy on training text but 12% recall on rare language tasks. Is it good for production? Why not?

Answer: No, it is not good. The low recall on rare tasks means the model misses many important cases, even if it looks accurate on common text. This shows poor understanding of diverse language, so it may fail in real use.

Key Result

Low perplexity and balanced precision-recall indicate good LLM understanding and text generation.

Practice

1. Why do Large Language Models (LLMs) understand and generate text?

easy

A. Because they memorize every sentence they read

B. Because they use fixed rules written by humans

C. Because they learn patterns from large amounts of text data

D. Because they translate text into images first

Solution

1. Step 1: Understand how LLMs learn

   LLMs learn by analyzing many examples of text to find patterns and relationships between words.

2. Step 2: Recognize pattern learning enables text generation

   By learning these patterns, LLMs can predict and generate new text that makes sense.

3. Final Answer:

   Because they learn patterns from large amounts of text data -> Option C

4. Quick Check:

   Pattern learning = B [OK]

Hint: LLMs predict text based on learned patterns [OK]

Common Mistakes:

• Thinking LLMs memorize all text exactly
• Believing LLMs use fixed human rules
• Assuming LLMs convert text to images first

2. Which of the following is the correct way to describe how LLMs generate text?

easy

A. They randomly pick words without context

B. They predict the next word based on previous words

C. They translate text into numbers and back without patterns

D. They only repeat the first sentence they learned

Solution

1. Step 1: Identify the text generation method

   LLMs generate text by predicting the next word using the context of previous words.

2. Step 2: Eliminate incorrect options

   Random picking ignores context, translating without patterns is wrong, and repeating only the first sentence is false.

3. Final Answer:

   They predict the next word based on previous words -> Option B

4. Quick Check:

   Next word prediction = D [OK]

Hint: LLMs guess next words using context [OK]

Common Mistakes:

• Thinking words are chosen randomly
• Believing LLMs do not use context
• Assuming LLMs only repeat learned sentences

3. Consider this simplified code snippet simulating LLM text generation:

context = ['I', 'love']
next_word = 'cats'
output = ' '.join(context + [next_word])
print(output)

What will be printed?

medium

A. I love cats

B. cats I love

C. I love

D. love cats

Solution

1. Step 1: Understand the code concatenation

   The code joins the list ['I', 'love'] with ['cats'] to form ['I', 'love', 'cats'].

2. Step 2: Join list elements into a string

   Using ' '.join(...) creates the string 'I love cats'.

3. Final Answer:

   I love cats -> Option A

4. Quick Check:

   Joining words = C [OK]

Hint: Join words in order to form sentence [OK]

Common Mistakes:

• Mixing word order in output
• Forgetting to join all words
• Printing only part of the list

4. This code tries to generate text but has an error:

context = ['Hello', 'world']
next_word = 123
output = ' '.join(context + [next_word])
print(output)

What is the error and how to fix it?

medium

A. TypeError because next_word is int; fix by converting to string

B. SyntaxError because of missing colon; fix by adding colon

C. IndexError because list is empty; fix by adding words

D. No error; code runs fine

Solution

1. Step 1: Identify the error type

   Joining strings with an integer causes a TypeError because join expects strings.

2. Step 2: Fix the error by converting integer to string

   Convert next_word to string using str(next_word) before joining.

3. Final Answer:

   TypeError because next_word is int; fix by converting to string -> Option A

4. Quick Check:

   TypeError fix = A [OK]

Hint: Join needs all strings; convert numbers to string first [OK]

Common Mistakes:

• Thinking it's a syntax error
• Ignoring type mismatch in join
• Assuming code runs without error

5. You want an LLM to summarize a long article. Which approach helps the model understand and generate a good summary?

hard

A. Feed unrelated text and ask for a summary

B. Feed only the first sentence and ask for a summary

C. Feed random sentences from the article without order

D. Feed the entire article as input and ask for a summary

Solution

1. Step 1: Understand input relevance for summarization

   Providing the full article gives the LLM enough context to understand main points.

2. Step 2: Recognize why other options fail

   Using only the first sentence, random sentences, or unrelated text lacks context, leading to poor summaries.

3. Final Answer:

   Feed the entire article as input and ask for a summary -> Option D

4. Quick Check:

   Full context input = A [OK]

Hint: More context means better summaries [OK]

Common Mistakes:

• Using partial or random text as input
• Ignoring importance of full context
• Expecting summary from unrelated text