mlsanityData to 7 Oct 2026

Decomposing Complex Questions Makes Multi-Hop QA Easier and More Interpretable

arXiv 2110.13472 ↗First posted 26 Oct 2021cs.CLcited by 35

Not on the map. Why?

Abstract (arXiv)

Multi-hop QA requires the machine to answer complex questions through finding multiple clues and reasoning, and provide explanatory evidence to demonstrate the machine reasoning process. We propose Relation Extractor-Reader and Comparator (RERC), a three-stage framework based on complex question decomposition, which is the first work that the RERC model has been proposed and applied in solving the multi-hop QA challenges. The Relation Extractor decomposes the complex question, and then the Reader answers the sub-questions in turn, and finally the Comparator performs numerical comparison and summarizes all to get the final answer, where the entire process itself constitutes a complete reasoning evidence path. In the 2WikiMultiHopQA dataset, our RERC model has achieved the most advanced performance, with a winning joint F1 score of 53.58 on the leaderboard. All indicators of our RERC are close to human performance, with only 1.95 behind the human level in F1 score of support fact. At the same time, the evidence path provided by our RERC framework has excellent readability and faithfulness.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Builds on 24 of its 46 references that are in the map. First posted on arXiv 26 Oct 2021.

Builds on

24 of 46 references.

References · 24

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2017Graph Attention Networkscited by 8,854
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  5. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  6. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  7. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
  8. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,538
  9. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  10. 2015Pointer Networkscited by 882
  11. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 409
  12. 2017Constructing Datasets for Multi-hop Reading Comprehension Across Documentscited by 190
12 more
  1. 2017Unsupervised Neural Machine Translationcited by 148
  2. 2019Multi-hop Reading Comprehension through Question Decomposition and Rescoringcited by 119
  3. 2020Unsupervised Question Decomposition for Question Answeringcited by 118
  4. 2019Cognitive Graph for Multi-Hop Reading Comprehension at Scalecited by 65
  5. 2019Dynamically Fused Graph Network for Multi-hop Reasoningcited by 63
  6. 2018Question Answering by Reasoning Across Documents with Graph Convolutional Networkscited by 56
  7. 2019Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphscited by 53
  8. 2019Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extractioncited by 39
  9. 2019R4C: A Benchmark for Evaluating RC Systems to Get the Right Answer for the Right Reasoncited by 36
  10. 2018Neural Models for Reasoning over Multiple Mentions using Coreferencecited by 27
  11. 2018Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural Networkscited by 23
  12. 2019Coarse-grain Fine-grain Coattention Network for Multi-evidence Question Answeringcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 10; 2024: 9; 2025: 7; 2026: 4.

35 papers.

Sort:

By area:

  1. 2023Question Decomposition Improves the Faithfulness of Model-Generated Reasoningcited by 107
  2. 2024MoreHopQA: More Than Multi-hop Reasoningcited by 37
  3. 2023End-to-End Beam Retrieval for Multi-Hop Question Answeringcited by 35
  4. 2024Enhancing Ethical Explanations of Large Language Models through Iterative Symbolic Refinementcited by 16
  5. 2023Iterated Decomposition: Improving Science Q&A by Supervising Reasoning Processescited by 15
  6. 2023Semantic Decomposition of Question and SQL for Text-to-SQL Parsingcited by 13
  7. 2025DeepSieve: Information Sieving via LLM-as-a-Knowledge-Routercited by 13
  8. 2023Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answeringcited by 8
  9. 2022Complex Reading Comprehension Through Question Decompositioncited by 7
  10. 2025PRISM: Agentic Retrieval with LLMs for Multi-Hop Question Answeringcited by 7
  11. 2022Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answeringcited by 6
  12. 2024FSM: A Finite State Machine Based Zero-Shot Prompting Paradigm for Multi-Hop Question Answeringcited by 6
23 more
  1. 2024QRMeM: Unleash the Length Limitation through Question then Reflection Memory Mechanismcited by 5
  2. 2026PruneRAG: Confidence-Guided Query Decomposition Trees for Efficient Retrieval-Augmented Generationcited by 5
  3. 2022A Survey on Measuring and Mitigating Reasoning Shortcuts in Machine Reading Comprehensioncited by 4
  4. 2024DEXTER: A Benchmark for open-domain Complex Question Answering using LLMscited by 4
  5. 2025Think Before You Retrieve: Learning Test-Time Adaptive Search with Small Language Modelscited by 4
  6. 2023Divide & Conquer for Entailment-aware Multi-hop Evidence Retrievalcited by 3
  7. 2024GenSco: Can Question Decomposition based Passage Alignment improve Question Answering?cited by 3
  8. 2026Before Forgetting, Learn to Remember: Revisiting Foundational Learning Failures in LVLM Unlearning Benchmarkscited by 3
  9. 2022Ask to Understand: Question Generation for Multi-hop Question Answeringcited by 2
  10. 2023Analyzing the Effectiveness of the Underlying Reasoning Tasks in Multi-hop Question Answeringcited by 2
  11. 2023Uncertainty Guided Global Memory Improves Multi-Hop Question Answeringcited by 2
  12. 2024SG-FSM: A Self-Guiding Zero-Shot Prompting Paradigm for Multi-Hop Question Answering Based on Finite State Machinecited by 2
  13. 2025On Synthesizing Data for Context Attribution in Question Answeringcited by 2
  14. 2026Facet-Level Tracing of Evidence Uncertainty and Hallucination in RAGcited by 2
  15. 2022A Comprehensive Survey on Multi-hop Machine Reading Comprehension Approachescited by 1
  16. 2023Semantic Parsing for Complex Data Retrieval: Targeting Query Plans vs. SQL for No-Code Access to Relational Databasescited by 1
  17. 2024Adapting Abstract Meaning Representation Parsing to the Clinical Narrative -- the SPRING THYME parsercited by 1
  18. 2025The Structure-Content Trade-off in Knowledge Graph Retrievalcited by 1
  19. 2025Think Parallax: Solving Multi-Hop Problems via Multi-View Knowledge-Graph-Based Retrieval-Augmented Generationcited by 1
  20. 2025Leveraging Spreading Activation for Improved Document Retrieval in Knowledge-Graph-Based RAG Systemscited by 1
  21. 2023Perturbation-based Active Learning for Question Answeringcited by 0
  22. 2024X-AMR Annotation Toolcited by 0
  23. 2026SubSearch: Intermediate Rewards for Unsupervised Guided Reasoning in Complex Retrievalcited by 0