# Simple yet Effective Bridge Reasoning for Open-Domain Multi-Hop Question Answering

arXiv: https://arxiv.org/abs/1909.07597 · HTML: https://mlsanity.com/paper/1909.07597/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2019.

## Built on by (most cited first, 4 of 4)

- [Modeling Multi-hop Question Answering as Single Sequence Prediction](https://mlsanity.com/paper/2205.09226/) (2022)
- [Retrieval-enhanced Knowledge Editing in Language Models for Multi-Hop Question Answering](https://mlsanity.com/paper/2403.19631/) (2024)
- [Performance Prediction for Multi-hop Questions](https://mlsanity.com/paper/2308.06431/) (2023)
- [Can David Beat Goliath? On Multi-Hop Reasoning with Resource-Constrained Agents](https://mlsanity.com/paper/2601.21699/) (2026)

## Abstract (arXiv)

A key challenge of multi-hop question answering (QA) in the open-domain setting is to accurately retrieve the supporting passages from a large corpus. Existing work on open-domain QA typically relies on off-the-shelf information retrieval (IR) techniques to retrieve answer passages, i.e., the passages containing the groundtruth answers. However, IR-based approaches are insufficient for multi-hop questions, as the topic of the second or further hops is not explicitly covered by the question. To resolve this issue, we introduce a new sub-problem of open-domain multi-hop QA, which aims to recognize the bridge (i.e., the anchor that links to the answer passage) from the context of a set of start passages with a reading comprehension model. This model, the bridge reasoner, is trained with a weakly supervised signal and produces the candidate answer passages for the passage reader to extract the answer. On the full-wiki HotpotQA benchmark, we significantly improve the baseline method by 14 point F1. Without using any memory-inefficient contextual embeddings, our result is also competitive with the state-of-the-art that applies BERT in multiple modules.