ModelRefs / Open-Domain Question Answering — AI Glossary
Open-Domain Question Answering — AI Glossary
Question answering without constraining the answer to a specific document; the model must retrieve or recall facts from broad knowledge.
Overview
Open-domain QA (Natural Questions, TriviaQA, WebQuestions) tests whether a model knows or can find an answer anywhere in its parameters or retrieval corpus. Retrieval-augmented approaches (DPR+FiD) dominated pre-LLM; frontier LLMs answer many factoid questions parametrically. Still benefits from RAG for freshness and verifiability.
Reference details
| Topic | prompting |
|---|---|
| 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 Open-Domain Question Answering — AI Glossary.
Frequently asked questions
What is Open-Domain Question Answering?
Question answering without constraining the answer to a specific document; the model must retrieve or recall facts from broad knowledge.
What concepts are related to Open-Domain Question Answering?
Closely related concepts include retrieval pipeline, rag, multi document qa.