liveBook · Manning

Open-domain task

As explained in Retrieval Augmented Generation, The Foundational Ideas

Open-domain question answering is the task of answering questions on broad topics by retrieving evidence from a large external collection.

Open-domain question answering answers questions across nearly any topic by drawing on a massive external corpus rather than a subject-specific collection. It differs from open-book tasks: open-domain describes the breadth of possible questions, while open-book describes permission to consult sources such as Wikipedia or an enterprise database. section 3.1

A standard late-2010s architecture separated fast retrieval from deep reading. Sparse retrievers such as TF-IDF and BM25 searched millions of documents and selected likely passages; a reader such as BERT then extracted an answer. Later systems used dense retrieval and generation, trading exact grounding against synthesis and computational cost. section 3.1 section 4.5

Common approaches differ in where knowledge resides and what the system returns:

  • Parametric models such as T5 answer from memorized knowledge, but knowledge freezes at training time and hallucination remains possible. section 4.5
  • DPR retrieves relevant passages and extracts exact answer spans, grounding factual lookups but struggling when answers require synthesis. section 4.5
  • RAG combines a frozen DPR retriever with a BART generator, joining document grounding with generated answers through modular fine-tuning. section 4.5

Wikipedia-scale question answering

The Natural Questions benchmark asks systems to answer authentic questions such as “What is the ozone layer and how does it affect Earth?”, “Who plays Voldemort in the Harry Potter movies?”, and “When did the Soviet Union collapse?” from 21 million Wikipedia passages. section 4.5

Table 3.1 Symmetric search vs asymmetric search
  Feature  
  Symmetric Search  
  Asymmetric Search  
 Goal 
 Find similar text (twins) 
 Find answers to questions 
 Input 
 Similar length/structure 
 Short query vs. Long doc 
 Model 
 SBERT 
 DPR 
 Use Case 
 Paraphrase detection 
 Open Domain QA 

Use the comparison to distinguish symmetric similarity search from asymmetric question-to-document retrieval, the pattern required for open-domain question answering. section 3.1

How Retrieval Augmented Generation, The Foundational Ideas covers it

How deep it goes
Contrasts open-domain and open-book tasks, then traces retriever-reader pipelines from sparse retrieval to dense and generative approaches.
Examples
Uses Watson, Wikipedia-scale Natural Questions, and questions about ozone, Voldemort, and the Soviet Union.
What you can do after
Evaluate retrieval, extraction, and generation tradeoffs across open-domain question-answering architectures.
How it connects
Connects open-book tasks, information retrieval, sparse retrieval, dense passage retrieval, BERT, T5, REALM, and RAG.

Also explained in

Compare how 2 books explain open-domain task →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Retrieval Augmented Generation, The Foundational Ideas. The section links point to the parts of the book it draws on.