QA Is the New KR: Question-Answer Pairs as Knowledge Bases
Not on the map. Why?
Abstract (arXiv)
In this position paper, we propose a new approach to generating a type of knowledge base (KB) from text, based on question generation and entity linking. We argue that the proposed type of KB has many of the key advantages of a traditional symbolic KB: in particular, it consists of small modular components, which can be combined compositionally to answer complex queries, including relational queries and queries involving "multi-hop" inferences. However, unlike a traditional KB, this information store is well-aligned with common user information needs.
Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 30 of its 55 references that are in the map. First posted on arXiv 1 Jul 2022.
Builds on
30 of 55 references.
References · 30
- 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
- 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
- 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
- 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
- 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
- 2017Zero-Shot Relation Extraction via Reading Comprehensioncited by 425
- 2020FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarizationcited by 292
- 2021PAQ: 65 Million Probably-Asked Questions and What You Can Do With Themcited by 198
- 2020Generation-Augmented Retrieval for Open-domain Question Answeringcited by 186
- 2020Break It Down: A Question Understanding Benchmarkcited by 131
- 2021Q2: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answeringcited by 131
- 2022Training Language Models with Memory Augmentationcited by 112
18 more
- 2020Entities as Experts: Sparse Memory Access with Entity Supervisioncited by 100
- 2020Learning Dense Representations of Phrases at Scalecited by 91
- 2020QED: A Framework and Dataset for Explanations in Question Answeringcited by 55
- 2018Large-Scale QA-SRL Parsingcited by 45
- 2021Mention Memory: incorporating textual knowledge into Transformers through entity mention attentioncited by 42
- 2020Differentiable Reasoning over a Virtual Knowledge Basecited by 39
- 2020Semantic Graphs for Generating Deep Questionscited by 38
- 2020Unsupervised Multi-hop Question Answering by Question Generationcited by 38
- 2020QADiscourse -- Discourse Relations as QA Pairs: Representation, Crowdsourcing and Baselinescited by 34
- 2017Semi-Supervised QA with Generative Domain-Adaptive Netscited by 27
- 2018Phrase-Indexed Question Answering: A New Challenge for Scalable Document Comprehensioncited by 23
- 2017Crowdsourcing Question-Answer Meaning Representationscited by 21
- 2020Harvesting and Refining Question-Answer Pairs for Unsupervised QAcited by 20
- 2021Question Answering Infused Pre-training of General-Purpose Contextualized Representationscited by 19
- 2022Augmenting Pre-trained Language Models with QA-Memory for Open-Domain Question Answeringcited by 19
- 2021Reasoning Over Virtual Knowledge Bases With Open Predicate Relationscited by 18
- 2019A Bilingual Generative Transformer for Semantic Sentence Embeddingcited by 16
- 2021QA-Align: Representing Cross-Text Content Overlap by Aligning Question-Answer Propositionscited by 16
Built on by
Citing papers per year: 2022: 1; 2023: 1; 2024: 1; 2025: 1; 2026: 2.
6 papers.
- 2022A Survey on Table-and-Text HybridQA: Concepts, Methods, Challenges and Future Directionscited by 7
- 2025How to Mitigate Information Loss in Knowledge Graphs for GraphRAG: Leveraging Triple Context Restoration and Query-Driven Feedbackcited by 6
- 2023Answering Ambiguous Questions with a Database of Questions, Answers, and Revisionscited by 4
- 2024QAEA-DR: A Unified Text Augmentation Framework for Dense Retrievalcited by 4
- 2026SocraticKG: Knowledge Graph Construction via QA-Driven Fact Extractioncited by 0
- 2026MDER-DR: Multi-Hop Question Answering with Entity-Centric Summariescited by 0
- 2026MDER-DR: Multi-Hop Question Answering with Entity-Centric Summaries11 Mar 2026
- 2026SocraticKG: Knowledge Graph Construction via QA-Driven Fact Extraction15 Jan 2026
- 2025How to Mitigate Information Loss in Knowledge Graphs for GraphRAG: Leveraging Triple Context Restoration and Query-Driven Feedback26 Jan 2025
- 2024QAEA-DR: A Unified Text Augmentation Framework for Dense Retrieval29 Jul 2024
- 2023Answering Ambiguous Questions with a Database of Questions, Answers, and Revisions16 Aug 2023
- 2022A Survey on Table-and-Text HybridQA: Concepts, Methods, Challenges and Future Directions27 Dec 2022