# Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering

arXiv: https://arxiv.org/abs/2208.10297 · HTML: https://mlsanity.com/paper/2208.10297/

## Key facts

- Cited by 6 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 25 of its 36 references that are in the map.
- First posted on arXiv 22 Aug 2022.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 25 of 25)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [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)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [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)
- [Break It Down: A Question Understanding Benchmark](https://mlsanity.com/paper/2001.11770/) (2020)
- [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)
- [Hierarchical Graph Network for Multi-hop Question Answering](https://mlsanity.com/paper/1911.03631/) (2019)
- [Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models](https://mlsanity.com/paper/2009.00751/) (2020)
- [Dynamically Fused Graph Network for Multi-hop Reasoning](https://mlsanity.com/paper/1905.06933/) (2019)
- [Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documents](https://mlsanity.com/paper/1911.00484/) (2019)
- [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)
- [Unsupervised Multi-hop Question Answering by Question Generation](https://mlsanity.com/paper/2010.12623/) (2020)
- [Span Selection Pre-training for Question Answering](https://mlsanity.com/paper/1909.04120/) (2019)
- [Decomposing Complex Questions Makes Multi-Hop QA Easier and More Interpretable](https://mlsanity.com/paper/2110.13472/) (2021)
- [Self-Assembling Modular Networks for Interpretable Multi-Hop Reasoning](https://mlsanity.com/paper/1909.05803/) (2019)
- [Neural Models for Reasoning over Multiple Mentions using Coreference](https://mlsanity.com/paper/1804.05922/) (2018)
- [Is Graph Structure Necessary for Multi-hop Question Answering?](https://mlsanity.com/paper/2004.03096/) (2020)

## Built on by (most cited first, 6 of 6)

- [Synergistic Multi-Agent Framework with Trajectory Learning for Knowledge-Intensive Tasks](https://mlsanity.com/paper/2407.09893/) (2024)
- [MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail Knowledge](https://mlsanity.com/paper/2412.17032/) (2024)
- [Iterated Decomposition: Improving Science Q&A by Supervising Reasoning Processes](https://mlsanity.com/paper/2301.01751/) (2023)
- [GenDec: A robust generative Question-decomposition method for Multi-hop reasoning](https://mlsanity.com/paper/2402.11166/) (2024)
- [Long-form Question Answering: An Iterative Planning-Retrieval-Generation Approach](https://mlsanity.com/paper/2311.09383/) (2023)
- [Uncertainty Guided Global Memory Improves Multi-Hop Question Answering](https://mlsanity.com/paper/2311.18151/) (2023)

## Abstract (arXiv)

Multi-hop reasoning requires aggregating multiple documents to answer a complex question. Existing methods usually decompose the multi-hop question into simpler single-hop questions to solve the problem for illustrating the explainable reasoning process. However, they ignore grounding on the supporting facts of each reasoning step, which tends to generate inaccurate decompositions. In this paper, we propose an interpretable stepwise reasoning framework to incorporate both single-hop supporting sentence identification and single-hop question generation at each intermediate step, and utilize the inference of the current hop for the next until reasoning out the final result. We employ a unified reader model for both intermediate hop reasoning and final hop inference and adopt joint optimization for more accurate and robust multi-hop reasoning. We conduct experiments on two benchmark datasets HotpotQA and 2WikiMultiHopQA. The results show that our method can effectively boost performance and also yields a better interpretable reasoning process without decomposition supervision.