EMNLP Findings2021
Decomposing Complex Questions Makes Multi-Hop QA Easier and More Interpretable
Abstract
Multi-hop QA requires the machine to answer complex questions through finding multiple clues and reasoning, and provide explanatory evidence to demonstrate the machine's reasoning process. We propose Relation Extractor-Reader and Comparator (RERC), a three-stage framework based on complex question decomposition. 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 state-of-the-art 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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
4 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answering cites Unsupervised Question Decomposition for Question Answering
- Think Parallax: Solving Multi-Hop Problems via Multi-View Knowledge-Graph-Based Retrieval-Augmented Generation cites Unsupervised Question Decomposition for Question Answering
Cited by top-tier papers4
- Chain-of-Questions Training with Latent Answers for Robust Multistep Question AnsweringWang Zhu, Jesse Thomason, Robin JiaEMNLP 2023 · 2 citations
- PruneRAG: Confidence-Guided Query Decomposition Trees for Efficient Retrieval-Augmented GenerationShuguang Jiao, Xinyu Xiao, Yunfan Wei, Shuhan Qi et al.WWW 2026 · 2 citations
- On Synthesizing Data for Context Attribution in Question AnsweringGorjan Radevski, Kiril Gashteovski, Shahbaz Syed, Christopher Malon et al.ACL 2025 · 1 citation
- Think Parallax: Solving Multi-Hop Problems via Multi-View Knowledge-Graph-Based Retrieval-Augmented GenerationJinliang Liu, Jiale Bai, Shaoning ZengACL 2026 · 1 citation
Builds on2
- ALBERT: A Lite BERT for Self-supervised Learning of Language RepresentationsZhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel et al.ICLR 2020 · 7,418 citations
- Unsupervised Question Decomposition for Question AnsweringEthan Perez, Patrick Lewis, Wen-tau Yih, Kyunghyun Cho et al.EMNLP 2020 · 6 citations
Related papers
- Triple-Fact Retriever: An explainable reasoning retrieval model for multi-hop QA problemChengmin Wu, Enrui Hu, Ke Zhan, Lan Luo et al.ICDE 2022 · 5 citations
- HopRetriever: Retrieve Hops over Wikipedia to Answer Complex QuestionsShaobo Li, Xiaoguang Li, Lifeng Shang, Xin Jiang et al.AAAI 2021 · 36 citations
- Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question AnsweringAkari Asai, Kazuma Hashimoto, Hannaneh Hajishirzi, Richard Socher et al.ICLR 2020 · 322 citations
- MultiModalQA: complex question answering over text, tables and imagesAlon Talmor, Ori Yoran, Amnon Catav, Dan Lahav et al.ICLR 2021 · 229 citations
- Modeling Multi-hop Question Answering as Single Sequence PredictionSemih Yavuz, Kazuma Hashimoto, Yingbo Zhou, Nitish Shirish Keskar et al.ACL 2022 · 35 citations
