mlsanityData to 14 Oct 2026

Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledge

arXiv 2210.12338 ↗First posted 22 Oct 2022cs.CLcited by 14

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

We propose a novel open-domain question answering (ODQA) framework for answering single/multi-hop questions across heterogeneous knowledge sources. The key novelty of our method is the introduction of the intermediary modules into the current retriever-reader pipeline. Unlike previous methods that solely rely on the retriever for gathering all evidence in isolation, our intermediary performs a chain of reasoning over the retrieved set. Specifically, our method links the retrieved evidence with its related global context into graphs and organizes them into a candidate list of evidence chains. Built upon pretrained language models, our system achieves competitive performance on two ODQA datasets, OTT-QA and NQ, against tables and passages from Wikipedia. In particular, our model substantially outperforms the previous state-of-the-art on OTT-QA with an exact match score of 47.3 (45 % relative gain).

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 38 of its 50 references that are in the map. First posted on arXiv 22 Oct 2022.

Builds on

38 of 50 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Reasoning over Hybrid Chain for Table-and-Text Open Domain QA15 Jan

Other references · 37

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  5. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  6. 2017Billion-scale similarity search with GPUscited by 2,497
  7. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,470
  8. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  9. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  10. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
  11. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 695
  12. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 410
25 more
  1. 2019Matching the Blanks: Distributional Similarity for Relation Learningcited by 272
  2. 2020HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Datacited by 264
  3. 2019PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Textcited by 184
  4. 2017Variational Reasoning for Question Answering with Knowledge Graphcited by 170
  5. 2021FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured informationcited by 167
  6. 2022Improving Passage Retrieval with Zero-Shot Question Generationcited by 165
  7. 2020Open Question Answering over Tables and Textcited by 163
  8. 2020Answering Complex Open-Domain Questions with Multi-Hop Dense Retrievalcited by 162
  9. 2019Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answeringcited by 147
  10. 2022CommonsenseQA 2.0: Exposing the Limits of AI through Gamificationcited by 109
  11. 2021Case-based Reasoning for Natural Language Queries over Knowledge Basescited by 107
  12. 2022DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Basescited by 84
  13. 2019Cognitive Graph for Multi-Hop Reading Comprehension at Scalecited by 65
  14. 2020UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answeringcited by 61
  15. 2019Answering Complex Open-domain Questions Through Iterative Query Generationcited by 60
  16. 2019Revealing the Importance of Semantic Retrieval for Machine Reading at Scalecited by 50
  17. 2020Answering Open-Domain Questions of Varying Reasoning Steps from Textcited by 43
  18. 2021UnitedQA: A Hybrid Approach for Open Domain Question Answeringcited by 42
  19. 2019Multi-Hop Paragraph Retrieval for Open-Domain Question Answeringcited by 34
  20. 2021Open Domain Question Answering with A Unified Knowledge Interfacecited by 32
  21. 2021Adaptive Information Seeking for Open-Domain Question Answeringcited by 29
  22. 2021Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrievalcited by 25
  23. 2021Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answeringcited by 25
  24. 2020Posterior Differential Regularization with f-divergence for Improving Model Robustnesscited by 20
  25. 2020Probabilistic Assumptions Matter: Improved Models for Distantly-Supervised Document-Level Question Answeringcited by 17

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 7; 2025: 2; 2026: 1.

14 papers.

Sort:

By area:

  1. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 354
  2. 2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 353
  3. 2023Retrieving Multimodal Information for Augmented Generation: A Surveycited by 85
  4. 2023Chain-of-Skills: A Configurable Model for Open-domain Question Answeringcited by 19
  5. 2024SPAGHETTI: Open-Domain Question Answering from Heterogeneous Data Sources with Retrieval and Semantic Parsingcited by 11
  6. 2022A Survey on Table-and-Text HybridQA: Concepts, Methods, Challenges and Future Directionscited by 7
  7. 2025Hybrid Graphs for Table-and-Text based Question Answering using LLMscited by 7
  8. 2024TTQA-RS- A break-down prompting approach for Multi-hop Table-Text Question Answering with Reasoning and Summarizationcited by 6
  9. 2024UniHGKR: Unified Instruction-aware Heterogeneous Knowledge Retrieverscited by 5
  10. 2024DEXTER: A Benchmark for open-domain Complex Question Answering using LLMscited by 4
  11. 2024Denoising Table-Text Retrieval for Open-Domain Question Answeringcited by 1
  12. 2026HELIOS: Harmonizing Early Fusion, Late Fusion, and LLM Reasoning for Multi-Granular Table-Text Retrievalcited by 1
2 more
  1. 2024Question Answering with Texts and Tables through Deep Reinforcement Learningcited by 0
  2. 2025GOSU: Retrieval-Augmented Generation with Global-Level Optimized Semantic Unit-Centric Frameworkcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Self-prompted Chain-of-Thought on Large Language Models for Open-domain Multi-hop Reasoning
  2. 2024Conv-CoA: Improving Open-domain Question Answering in Large Language Models via Conversational Chain-of-Action
  3. 2024TANQ: An open domain dataset of table answered questions
  4. 2026Gradually Excavating External Knowledge for Implicit Complex Question Answering
  5. 2025StepChain GraphRAG: Reasoning Over Knowledge Graphs for Multi-Hop Question Answering
  6. 2023DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text
  7. 2022Better Retrieval May Not Lead to Better Question Answering
  8. 2025Beyond Chains: Bridging Large Language Models and Knowledge Bases in Complex Question Answering