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

arXiv: https://arxiv.org/abs/2110.13472 · HTML: https://mlsanity.com/paper/2110.13472/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 46 references that are in the map.
- First posted on arXiv 26 Oct 2021.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Pointer Networks](https://mlsanity.com/paper/1506.03134/) (2015)
- [The Web as a Knowledge-base for Answering Complex Questions](https://mlsanity.com/paper/1803.06643/) (2018)
- [Constructing Datasets for Multi-hop Reading Comprehension Across Documents](https://mlsanity.com/paper/1710.06481/) (2017)
- [Unsupervised Neural Machine Translation](https://mlsanity.com/paper/1710.11041/) (2017)
- [Multi-hop Reading Comprehension through Question Decomposition and Rescoring](https://mlsanity.com/paper/1906.02916/) (2019)
- [Unsupervised Question Decomposition for Question Answering](https://mlsanity.com/paper/2002.09758/) (2020)
- [Cognitive Graph for Multi-Hop Reading Comprehension at Scale](https://mlsanity.com/paper/1905.05460/) (2019)
- [Dynamically Fused Graph Network for Multi-hop Reasoning](https://mlsanity.com/paper/1905.06933/) (2019)
- [Question Answering by Reasoning Across Documents with Graph Convolutional Networks](https://mlsanity.com/paper/1808.09920/) (2018)
- [Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs](https://mlsanity.com/paper/1905.07374/) (2019)
- [Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extraction](https://mlsanity.com/paper/1905.08511/) (2019)
- [R4C: A Benchmark for Evaluating RC Systems to Get the Right Answer for the Right Reason](https://mlsanity.com/paper/1910.04601/) (2019)
- [Neural Models for Reasoning over Multiple Mentions using Coreference](https://mlsanity.com/paper/1804.05922/) (2018)
- [Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural Networks](https://mlsanity.com/paper/1809.02040/) (2018)
- [Coarse-grain Fine-grain Coattention Network for Multi-evidence Question Answering](https://mlsanity.com/paper/1901.00603/) (2019)

## Built on by (most cited first, 30 of 35)

- [Question Decomposition Improves the Faithfulness of Model-Generated Reasoning](https://mlsanity.com/paper/2307.11768/) (2023)
- [MoreHopQA: More Than Multi-hop Reasoning](https://mlsanity.com/paper/2406.13397/) (2024)
- [End-to-End Beam Retrieval for Multi-Hop Question Answering](https://mlsanity.com/paper/2308.08973/) (2023)
- [Enhancing Ethical Explanations of Large Language Models through Iterative Symbolic Refinement](https://mlsanity.com/paper/2402.00745/) (2024)
- [Iterated Decomposition: Improving Science Q&A by Supervising Reasoning Processes](https://mlsanity.com/paper/2301.01751/) (2023)
- [Semantic Decomposition of Question and SQL for Text-to-SQL Parsing](https://mlsanity.com/paper/2310.13575/) (2023)
- [DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router](https://mlsanity.com/paper/2507.22050/) (2025)
- [Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answering](https://mlsanity.com/paper/2305.14901/) (2023)
- [PRISM: Agentic Retrieval with LLMs for Multi-Hop Question Answering](https://mlsanity.com/paper/2510.14278/) (2025)
- [Complex Reading Comprehension Through Question Decomposition](https://mlsanity.com/paper/2211.03277/) (2022)
- [Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering](https://mlsanity.com/paper/2208.10297/) (2022)
- [QRMeM: Unleash the Length Limitation through Question then Reflection Memory Mechanism](https://mlsanity.com/paper/2406.13167/) (2024)
- [FSM: A Finite State Machine Based Zero-Shot Prompting Paradigm for Multi-Hop Question Answering](https://mlsanity.com/paper/2407.02964/) (2024)
- [Think Before You Retrieve: Learning Test-Time Adaptive Search with Small Language Models](https://mlsanity.com/paper/2511.07581/) (2025)
- [PruneRAG: Confidence-Guided Query Decomposition Trees for Efficient Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.11024/) (2026)
- [A Survey on Measuring and Mitigating Reasoning Shortcuts in Machine Reading Comprehension](https://mlsanity.com/paper/2209.01824/) (2022)
- [DEXTER: A Benchmark for open-domain Complex Question Answering using LLMs](https://mlsanity.com/paper/2406.17158/) (2024)
- [Divide & Conquer for Entailment-aware Multi-hop Evidence Retrieval](https://mlsanity.com/paper/2311.02616/) (2023)
- [GenSco: Can Question Decomposition based Passage Alignment improve Question Answering?](https://mlsanity.com/paper/2407.10245/) (2024)
- [Before Forgetting, Learn to Remember: Revisiting Foundational Learning Failures in LVLM Unlearning Benchmarks](https://mlsanity.com/paper/2605.03759/) (2026)
- [Ask to Understand: Question Generation for Multi-hop Question Answering](https://mlsanity.com/paper/2203.09073/) (2022)
- [Analyzing the Effectiveness of the Underlying Reasoning Tasks in Multi-hop Question Answering](https://mlsanity.com/paper/2302.05963/) (2023)
- [Uncertainty Guided Global Memory Improves Multi-Hop Question Answering](https://mlsanity.com/paper/2311.18151/) (2023)
- [SG-FSM: A Self-Guiding Zero-Shot Prompting Paradigm for Multi-Hop Question Answering Based on Finite State Machine](https://mlsanity.com/paper/2410.17021/) (2024)
- [On Synthesizing Data for Context Attribution in Question Answering](https://mlsanity.com/paper/2504.05317/) (2025)
- [Facet-Level Tracing of Evidence Uncertainty and Hallucination in RAG](https://mlsanity.com/paper/2604.09174/) (2026)
- [A Comprehensive Survey on Multi-hop Machine Reading Comprehension Approaches](https://mlsanity.com/paper/2212.04072/) (2022)
- [Semantic Parsing for Complex Data Retrieval: Targeting Query Plans vs. SQL for No-Code Access to Relational Databases](https://mlsanity.com/paper/2312.14798/) (2023)
- [Adapting Abstract Meaning Representation Parsing to the Clinical Narrative -- the SPRING THYME parser](https://mlsanity.com/paper/2405.09153/) (2024)
- [The Structure-Content Trade-off in Knowledge Graph Retrieval](https://mlsanity.com/paper/2506.13380/) (2025)

## 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.