# Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering

arXiv: https://arxiv.org/abs/2005.01218 · HTML: https://mlsanity.com/paper/2005.01218/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 May 2020.

## Built on by (most cited first, 24 of 24)

- [Incorporating External Knowledge to Enhance Tabular Reasoning](https://mlsanity.com/paper/2104.04243/) (2021)
- [Skimming, Locating, then Perusing: A Human-Like Framework for Natural Language Video Localization](https://mlsanity.com/paper/2207.13450/) (2022)
- [Retrieval-enhanced Knowledge Editing in Language Models for Multi-Hop Question Answering](https://mlsanity.com/paper/2403.19631/) (2024)
- [Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering](https://mlsanity.com/paper/2105.11776/) (2021)
- [METGEN: A Module-Based Entailment Tree Generation Framework for Answer Explanation](https://mlsanity.com/paper/2205.02593/) (2022)
- [Enhancing Ethical Explanations of Large Language Models through Iterative Symbolic Refinement](https://mlsanity.com/paper/2402.00745/) (2024)
- [Exploiting Reasoning Chains for Multi-hop Science Question Answering](https://mlsanity.com/paper/2109.02905/) (2021)
- [Robustifying Multi-hop QA through Pseudo-Evidentiality Training](https://mlsanity.com/paper/2107.03242/) (2021)
- [Retrieval-Enhanced Machine Learning: Synthesis and Opportunities](https://mlsanity.com/paper/2407.12982/) (2024)
- [Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehension](https://mlsanity.com/paper/2109.06853/) (2021)
- [Diff-Explainer: Differentiable Convex Optimization for Explainable Multi-hop Inference](https://mlsanity.com/paper/2105.03417/) (2021)
- [Cheap and Good? Simple and Effective Data Augmentation for Low Resource Machine Reading](https://mlsanity.com/paper/2106.04134/) (2021)
- [Distinguish Before Answer: Generating Contrastive Explanation as Knowledge for Commonsense Question Answering](https://mlsanity.com/paper/2305.08135/) (2023)
- [Evaluating Concurrent Robustness of Language Models Across Diverse Challenge Sets](https://mlsanity.com/paper/2311.08662/) (2023)
- [Diversifying Query: Region-Guided Transformer for Temporal Sentence Grounding](https://mlsanity.com/paper/2406.00143/) (2024)
- [HOP, UNION, GENERATE: Explainable Multi-hop Reasoning without Rationale Supervision](https://mlsanity.com/paper/2305.14237/) (2023)
- [Post-Hoc Answer Attribution for Grounded and Trustworthy Long Document Comprehension: Task, Insights, and Challenges](https://mlsanity.com/paper/2406.06938/) (2024)
- [Classification of Goods Using Text Descriptions With Sentences Retrieval](https://mlsanity.com/paper/2111.01663/) (2021)
- [Enhancing Tabular Reasoning with Pattern Exploiting Training](https://mlsanity.com/paper/2210.12259/) (2022)
- [Explainable Product Classification for Customs](https://mlsanity.com/paper/2311.10922/) (2023)
- [Explicit Diversity Conditions for Effective Question Answer Generation with Large Language Models](https://mlsanity.com/paper/2406.17990/) (2024)
- [UFO: Unified Fact Obtaining for Commonsense Question Answering](https://mlsanity.com/paper/2305.16048/) (2023)
- [Integrating Hierarchical Semantic into Iterative Generation Model for Entailment Tree Explanation](https://mlsanity.com/paper/2409.17757/) (2024)
- [Say Less, Mean More: Leveraging Pragmatics in Retrieval-Augmented Generation](https://mlsanity.com/paper/2502.17839/) (2025)

## Abstract (arXiv)

Evidence retrieval is a critical stage of question answering (QA), necessary not only to improve performance, but also to explain the decisions of the corresponding QA method. We introduce a simple, fast, and unsupervised iterative evidence retrieval method, which relies on three ideas: (a) an unsupervised alignment approach to soft-align questions and answers with justification sentences using only GloVe embeddings, (b) an iterative process that reformulates queries focusing on terms that are not covered by existing justifications, which (c) a stopping criterion that terminates retrieval when the terms in the given question and candidate answers are covered by the retrieved justifications. Despite its simplicity, our approach outperforms all the previous methods (including supervised methods) on the evidence selection task on two datasets: MultiRC and QASC. When these evidence sentences are fed into a RoBERTa answer classification component, we achieve state-of-the-art QA performance on these two datasets.