# From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answering

arXiv: https://arxiv.org/abs/2205.11729 · HTML: https://mlsanity.com/paper/2205.11729/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 37 references that are in the map.
- First posted on arXiv 24 May 2022.

## Builds on (most cited first, 30 of 30)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [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)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [The Web as a Knowledge-base for Answering Complex Questions](https://mlsanity.com/paper/1803.06643/) (2018)
- [Bidirectional Attention Flow for Machine Comprehension](https://mlsanity.com/paper/1611.01603/) (2016)
- [SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine](https://mlsanity.com/paper/1704.05179/) (2017)
- [Constructing Datasets for Multi-hop Reading Comprehension Across Documents](https://mlsanity.com/paper/1710.06481/) (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)
- [Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering](https://mlsanity.com/paper/1908.08167/) (2019)
- [Compositional Questions Do Not Necessitate Multi-hop Reasoning](https://mlsanity.com/paper/1906.02900/) (2019)
- [Hierarchical Graph Network for Multi-hop Question Answering](https://mlsanity.com/paper/1911.03631/) (2019)
- [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)
- [Avoiding Reasoning Shortcuts: Adversarial Evaluation, Training, and Model Development for Multi-Hop QA](https://mlsanity.com/paper/1906.07132/) (2019)
- [Answering Complex Open-domain Questions Through Iterative Query Generation](https://mlsanity.com/paper/1910.07000/) (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)
- [Dynamic Coattention Networks For Question Answering](https://mlsanity.com/paper/1611.01604/) (2016)
- [Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering](https://mlsanity.com/paper/1905.05733/) (2019)
- [Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extraction](https://mlsanity.com/paper/1905.08511/) (2019)
- [Multi-Hop Paragraph Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/1906.06606/) (2019)
- [Neural Models for Reasoning over Multiple Mentions using Coreference](https://mlsanity.com/paper/1804.05922/) (2018)
- [Efficient and Robust Question Answering from Minimal Context over Documents](https://mlsanity.com/paper/1805.08092/) (2018)
- [A Simple Yet Strong Pipeline for HotpotQA](https://mlsanity.com/paper/2004.06753/) (2020)
- [Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural Networks](https://mlsanity.com/paper/1809.02040/) (2018)
- [Graph-free Multi-hop Reading Comprehension: A Select-to-Guide Strategy](https://mlsanity.com/paper/2107.11823/) (2021)

## Built on by (most cited first, 12 of 12)

- [End-to-End Beam Retrieval for Multi-Hop Question Answering](https://mlsanity.com/paper/2308.08973/) (2023)
- [CRUSH4SQL: Collective Retrieval Using Schema Hallucination For Text2SQL](https://mlsanity.com/paper/2311.01173/) (2023)
- [GenDec: A robust generative Question-decomposition method for Multi-hop reasoning](https://mlsanity.com/paper/2402.11166/) (2024)
- [Relational Programming with Foundation Models](https://mlsanity.com/paper/2412.14515/) (2024)
- [HOP, UNION, GENERATE: Explainable Multi-hop Reasoning without Rationale Supervision](https://mlsanity.com/paper/2305.14237/) (2023)
- [Single Sequence Prediction over Reasoning Graphs for Multi-hop QA](https://mlsanity.com/paper/2307.00335/) (2023)
- [Rethinking Label Smoothing on Multi-hop Question Answering](https://mlsanity.com/paper/2212.09512/) (2022)
- [Gumbel Reranking: Differentiable End-to-End Reranker Optimization](https://mlsanity.com/paper/2502.11116/) (2025)
- [Challenges in Explanation Quality Evaluation](https://mlsanity.com/paper/2210.07126/) (2022)
- [M3: A Multi-Task Mixed-Objective Learning Framework for Open-Domain Multi-Hop Dense Sentence Retrieval](https://mlsanity.com/paper/2403.14074/) (2024)
- [emrQA-msquad: A Medical Dataset Structured with the SQuAD V2.0 Framework, Enriched with emrQA Medical Information](https://mlsanity.com/paper/2404.12050/) (2024)
- [Bactrainus: Optimizing Large Language Models for Multi-hop Complex Question Answering Tasks](https://mlsanity.com/paper/2501.06286/) (2025)

## Abstract (arXiv)

Multi-hop question answering (QA) is a challenging task requiring QA systems to perform complex reasoning over multiple documents and provide supporting facts together with the exact answer. Existing works tend to utilize graph-based reasoning and question decomposition to obtain the reasoning chain, which inevitably introduces additional complexity and cumulative error to the system. To address the above issue, we propose a simple yet effective novel framework, From Easy to Hard (FE2H), to remove distracting information and obtain better contextual representations for the multi-hop QA task. Inspired by the iterative document selection process and the progressive learning custom of humans, FE2H divides both the document selector and reader into two stages following an easy-to-hard manner. Specifically, we first select the document most relevant to the question and then utilize the question together with this document to select other pertinent documents. As for the QA phase, our reader is first trained on a single-hop QA dataset and then transferred into the multi-hop QA task. We comprehensively evaluate our model on the popular multi-hop QA benchmark HotpotQA. Experimental results demonstrate that our method ourperforms all other methods in the leaderboard of HotpotQA (distractor setting).