# Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering

arXiv: https://arxiv.org/abs/1909.07598 · HTML: https://mlsanity.com/paper/1909.07598/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2019.

## Built on by (most cited first, 20 of 20)

- [HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models](https://mlsanity.com/paper/2405.14831/) (2024)
- [Retrieval-Enhanced Machine Learning](https://mlsanity.com/paper/2205.01230/) (2022)
- [Adaptive Information Seeking for Open-Domain Question Answering](https://mlsanity.com/paper/2109.06747/) (2021)
- [Entity Linking and Discovery via Arborescence-based Supervised Clustering](https://mlsanity.com/paper/2109.01242/) (2021)
- [Retrieval-enhanced Knowledge Editing in Language Models for Multi-Hop Question Answering](https://mlsanity.com/paper/2403.19631/) (2024)
- [You can't pick your neighbors, or can you? When and how to rely on retrieval in the kNN-LM](https://mlsanity.com/paper/2210.15859/) (2022)
- [Multi-hop Evidence Retrieval for Cross-document Relation Extraction](https://mlsanity.com/paper/2212.10786/) (2022)
- [Retrieval-Enhanced Machine Learning: Synthesis and Opportunities](https://mlsanity.com/paper/2407.12982/) (2024)
- [Counterfactual Multihop QA: A Cause-Effect Approach for Reducing Disconnected Reasoning](https://mlsanity.com/paper/2210.07138/) (2022)
- [NASTyLinker: NIL-Aware Scalable Transformer-based Entity Linker](https://mlsanity.com/paper/2303.04426/) (2023)
- [Single Sequence Prediction over Reasoning Graphs for Multi-hop QA](https://mlsanity.com/paper/2307.00335/) (2023)
- [Performance Prediction for Multi-hop Questions](https://mlsanity.com/paper/2308.06431/) (2023)
- [IterKey: Iterative Keyword Generation with LLMs for Enhanced Retrieval Augmented Generation](https://mlsanity.com/paper/2505.08450/) (2025)
- [Complementary Evidence Identification in Open-Domain Question Answering](https://mlsanity.com/paper/2103.11643/) (2021)
- [Open-domain Dialogue Generation Grounded with Dynamic Multi-form Knowledge Fusion](https://mlsanity.com/paper/2204.11239/) (2022)
- [Pre-training for Information Retrieval: Are Hyperlinks Fully Explored?](https://mlsanity.com/paper/2209.06583/) (2022)
- [Knowledge-Aware Iterative Retrieval for Multi-Agent Systems](https://mlsanity.com/paper/2503.13275/) (2025)
- [Entity-Augmented Neuroscience Knowledge Retrieval Using Ontology and Semantic Understanding Capability of LLM](https://mlsanity.com/paper/2506.03145/) (2025)
- [Evidence Blindness in Direct Corpus Interaction: Persistent Navigation with AtlasNav](https://mlsanity.com/paper/2608.24764/) (2026)
- [XHotpotQA: A Benchmark for Cross-Lingual Knowledge Composition in Multi-Hop Question Answering](https://mlsanity.com/paper/2608.27481/) (2026)

## Abstract (arXiv)

Multi-hop question answering (QA) requires an information retrieval (IR) system that can find multiple supporting evidence needed to answer the question, making the retrieval process very challenging. This paper introduces an IR technique that uses information of entities present in the initially retrieved evidence to learn to `hop' to other relevant evidence. In a setting, with more than 5 million Wikipedia paragraphs, our approach leads to significant boost in retrieval performance. The retrieved evidence also increased the performance of an existing QA model (without any training) on the hotpot benchmark by 10.59 F1.