# Repurposing Entailment for Multi-Hop Question Answering Tasks

arXiv: https://arxiv.org/abs/1904.09380 · HTML: https://mlsanity.com/paper/1904.09380/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Apr 2019.

## Built on by (most cited first, 10 of 10)

- [MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark](https://mlsanity.com/paper/2410.19168/) (2024)
- [Can NLI Models Verify QA Systems' Predictions?](https://mlsanity.com/paper/2104.08731/) (2021)
- [Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2112.08688/) (2021)
- [SILT: Efficient transformer training for inter-lingual inference](https://mlsanity.com/paper/2103.09635/) (2021)
- [PASTA: A Dataset for Modeling Participant States in Narratives](https://mlsanity.com/paper/2208.00329/) (2022)
- [CAPTAIN at COLIEE 2023: Efficient Methods for Legal Information Retrieval and Entailment Tasks](https://mlsanity.com/paper/2401.03551/) (2024)
- [Leveraging Data Recasting to Enhance Tabular Reasoning](https://mlsanity.com/paper/2211.12641/) (2022)
- [Discrepancy Detection at the Data Level: Toward Consistent Multilingual Question Answering](https://mlsanity.com/paper/2510.11928/) (2025)
- [HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering](https://mlsanity.com/paper/2509.09713/) (2025)
- [Using contradictions improves question answering systems](https://mlsanity.com/paper/2211.05598/) (2022)

## Abstract (arXiv)

Question Answering (QA) naturally reduces to an entailment problem, namely, verifying whether some text entails the answer to a question. However, for multi-hop QA tasks, which require reasoning with multiple sentences, it remains unclear how best to utilize entailment models pre-trained on large scale datasets such as SNLI, which are based on sentence pairs. We introduce Multee, a general architecture that can effectively use entailment models for multi-hop QA tasks. Multee uses (i) a local module that helps locate important sentences, thereby avoiding distracting information, and (ii) a global module that aggregates information by effectively incorporating importance weights. Importantly, we show that both modules can use entailment functions pre-trained on a large scale NLI datasets. We evaluate performance on MultiRC and OpenBookQA, two multihop QA datasets. When using an entailment function pre-trained on NLI datasets, Multee outperforms QA models trained only on the target QA datasets and the OpenAI transformer models. The code is available at https://github.com/StonyBrookNLP/multee.