Question answering in Prompt Engineering / GenAI - Full Explanation

Introduction

Imagine you have a huge book but need a quick answer to a specific question. Searching through all the pages takes too long. Question answering systems solve this by finding the exact information you want quickly and clearly.

Explanation

Understanding the Question

The system first reads and understands the question to know what information is being asked. It breaks down the question into key parts like the main topic and what kind of answer is needed. This helps the system focus on the right information.

Grasping the question clearly is the first step to finding the right answer.

Searching for Information

After understanding the question, the system looks through its data sources, like documents or databases, to find relevant information. It uses keywords and context from the question to narrow down the search to the most useful parts.

Efficient searching narrows down the vast information to what matters most.

Extracting the Answer

Once relevant information is found, the system extracts the exact answer. This might be a phrase, sentence, or a short explanation that directly responds to the question. The system ensures the answer is clear and concise.

Extracting a precise answer makes the response useful and easy to understand.

Presenting the Answer

Finally, the system presents the answer in a way that is easy to read and understand. Sometimes it adds extra context or explanations to help the user grasp the answer better. The goal is to make the answer helpful and user-friendly.

Clear presentation helps users quickly understand the answer.

Real World Analogy

Imagine asking a librarian a question in a huge library. The librarian listens carefully, quickly finds the right book and page, points out the exact sentence you need, and explains it clearly so you understand.

Understanding the Question → Librarian listening carefully to your question

Searching for Information → Librarian searching through books and shelves

Extracting the Answer → Librarian finding the exact sentence or paragraph

Presenting the Answer → Librarian explaining the answer clearly to you

Diagram

Diagram

┌─────────────────────┐
│ 1. Understand Question │
└──────────┬──────────┘
           │
           ↓
┌─────────────────────┐
│ 2. Search Information │
└──────────┬──────────┘
           │
           ↓
┌─────────────────────┐
│ 3. Extract Answer    │
└──────────┬──────────┘
           │
           ↓
┌─────────────────────┐
│ 4. Present Answer    │
└─────────────────────┘

This diagram shows the four main steps in a question answering system from understanding the question to presenting the answer.

Key Facts

Question Understanding → The process of interpreting the user's question to identify key information needs.

Information Retrieval → Finding relevant data or documents that may contain the answer.

Answer Extraction → Selecting the precise piece of information that answers the question.

Answer Presentation → Displaying the answer clearly and understandably to the user.

Context Awareness → Using the question's context to improve search and answer accuracy.

Common Confusions

Believing question answering systems just search keywords like a simple search engine.

Believing question answering systems just search keywords like a simple search engine. Question answering systems understand the meaning of the question and context, not just keywords, to find precise answers.

Thinking the system always gives a full document as an answer.

Thinking the system always gives a full document as an answer. The system extracts concise answers, not entire documents, to save time and improve clarity.

Summary

Question answering systems quickly find precise answers by understanding questions and searching relevant information.

They extract clear answers and present them in an easy-to-understand way.

This process is like a helpful librarian guiding you to the exact information you need.

Practice

1. What is the main purpose of question answering in AI?

easy

A. To find answers from given text or context

B. To generate random text without context

C. To translate languages automatically

D. To create images from descriptions

Solution

1. Step 1: Understand the goal of question answering

   Question answering systems are designed to find specific answers from a given text or context.

2. Step 2: Compare options with the goal

   Only To find answers from given text or context describes finding answers from text, which matches the purpose.

3. Final Answer:

   To find answers from given text or context -> Option A

4. Quick Check:

   Question answering = find answers [OK]

Hint: Focus on 'answer from text' meaning [OK]

Common Mistakes:

• Confusing question answering with translation
• Thinking it generates random text
• Mixing it with image generation

2. Which input is essential for a question answering model to work?

easy

A. Only a context without a question

B. Only a question without any context

C. A question and a related context or passage

D. Random text unrelated to the question

Solution

1. Step 1: Identify inputs needed for question answering

   Question answering requires both a question and some context to find the answer.

2. Step 2: Match options with required inputs

   Only A question and a related context or passage provides both question and related context, which is necessary.

3. Final Answer:

   A question and a related context or passage -> Option C

4. Quick Check:

   Question + context = answer [OK]

Hint: Remember: question needs context to answer [OK]

Common Mistakes:

• Assuming question alone is enough
• Ignoring the need for context
• Choosing unrelated text as input

3. Given this Python code using a question answering model:

from transformers import pipeline
qa = pipeline('question-answering')
context = "The Eiffel Tower is in Paris."
question = "Where is the Eiffel Tower located?"
result = qa(question=question, context=context)
print(result['answer'])

What will be printed?

medium

A. Location unknown

B. Eiffel Tower

C. The Eiffel Tower is in Paris

D. Paris

Solution

1. Step 1: Understand the code's purpose

   The code uses a question answering pipeline to find the answer to the question from the context.

2. Step 2: Identify the answer in the context

   The question asks for location; the context says "The Eiffel Tower is in Paris." So the answer is "Paris".

3. Final Answer:

   Paris -> Option D

4. Quick Check:

   Answer extracted = Paris [OK]

Hint: Look for direct answer in context matching question [OK]

Common Mistakes:

• Printing the whole context instead of answer
• Confusing object with location
• Assuming no answer found

4. This code snippet tries to answer a question but raises an error:

from transformers import pipeline
qa = pipeline('question-answering')
context = "Python is a programming language."
question = "What is Python?"
result = qa(question, context)
print(result['answer'])

What is the error and how to fix it?

medium

A. Error: question is invalid; fix by changing question text

B. Error: missing keyword arguments; fix by using qa(question=question, context=context)

C. Error: context is empty; fix by adding text to context

D. No error; code runs fine

Solution

1. Step 1: Identify the function call error

   The pipeline expects keyword arguments question= and context=, but code passes positional arguments.

2. Step 2: Fix the call with correct keywords

   Change to qa(question=question, context=context) to fix the error.

3. Final Answer:

   Error: missing keyword arguments; fix by using qa(question=question, context=context) -> Option B

4. Quick Check:

   Use keywords for qa() args [OK]

Hint: Use keyword arguments for question and context [OK]

Common Mistakes:

• Passing positional args instead of keywords
• Assuming empty context causes error
• Changing question text unnecessarily

5. You want to build a question answering system that can handle multiple paragraphs and find the best answer. Which approach is best?

hard

A. Split text into paragraphs, run QA on each, then pick highest confidence answer

B. Combine all paragraphs into one string and run QA once

C. Only use the first paragraph for QA

D. Ignore paragraphs and guess answer randomly

Solution

1. Step 1: Understand handling multiple paragraphs

   QA models usually work best on smaller text chunks, so splitting helps.

2. Step 2: Choose method to find best answer

   Running QA on each paragraph separately and selecting the answer with highest confidence ensures accuracy.

3. Final Answer:

   Split text into paragraphs, run QA on each, then pick highest confidence answer -> Option A

4. Quick Check:

   Split + score answers = best result [OK]

Hint: Split text, run QA per part, pick best answer [OK]

Common Mistakes:

• Running QA on all text at once causing confusion
• Ignoring paragraphs reduces accuracy
• Guessing answers without context