ModelRefs / Question Answering (QA) — AI Glossary
Question Answering (QA) — AI Glossary
Systems that automatically answer natural language questions from documents, knowledge bases, or model parameters. Also called QA or reading comprehension.
Overview
QA types: extractive (select span from text), abstractive (generate free-form answer), and closed-book (rely on parametric knowledge). LLMs perform abstractive QA well, especially with RAG for factual grounding. Benchmarks: SQuAD (extractive), Natural Questions, TriviaQA. Production QA systems combine retrieval with generation for verifiability.
Reference details
| Topic | applications |
|---|---|
| Also known as | QA, reading comprehension |
| Last reviewed | 2026-06-24 |
Related terms
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Question Answering (QA) — AI Glossary.
Frequently asked questions
What is Question Answering (QA)?
Systems that automatically answer natural language questions from documents, knowledge bases, or model parameters.
Is Question Answering (QA) the same as QA?
Yes — QA, reading comprehension are common aliases for Question Answering (QA).
What concepts are related to Question Answering (QA)?
Closely related concepts include open domain qa, multi document qa, rag.