# Multi-hop Question Answering via Reasoning Chains

arXiv: https://arxiv.org/abs/1910.02610 · HTML: https://mlsanity.com/paper/1910.02610/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2019.

## Built on by (most cited first, 30 of 42)

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Progressive-Hint Prompting Improves Reasoning in Large Language Models](https://mlsanity.com/paper/2304.09797/) (2023)
- [Rationale-Augmented Ensembles in Language Models](https://mlsanity.com/paper/2207.00747/) (2022)
- [From LSAT: The Progress and Challenges of Complex Reasoning](https://mlsanity.com/paper/2108.00648/) (2021)
- [Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2112.08688/) (2021)
- [RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement](https://mlsanity.com/paper/2412.12881/) (2024)
- [Natural Language Deduction through Search over Statement Compositions](https://mlsanity.com/paper/2201.06028/) (2022)
- [PokeMQA: Programmable knowledge editing for Multi-hop Question Answering](https://mlsanity.com/paper/2312.15194/) (2023)
- [Modeling Multi-hop Question Answering as Single Sequence Prediction](https://mlsanity.com/paper/2205.09226/) (2022)
- [Rethinking Search: Making Domain Experts out of Dilettantes](https://mlsanity.com/paper/2105.02274/) (2021)
- [Think Clearly: Improving Reasoning via Redundant Token Pruning](https://mlsanity.com/paper/2507.08806/) (2025)
- [Focus on what matters: Applying Discourse Coherence Theory to Cross Document Coreference](https://mlsanity.com/paper/2110.05362/) (2021)
- [Thinking Aloud: Dynamic Context Generation Improves Zero-Shot Reasoning Performance of GPT-2](https://mlsanity.com/paper/2103.13033/) (2021)
- [Exploiting Reasoning Chains for Multi-hop Science Question Answering](https://mlsanity.com/paper/2109.02905/) (2021)
- [Graph-free Multi-hop Reading Comprehension: A Select-to-Guide Strategy](https://mlsanity.com/paper/2107.11823/) (2021)
- [Hopper: Multi-hop Transformer for Spatiotemporal Reasoning](https://mlsanity.com/paper/2103.10574/) (2021)
- [Natural Language Deduction with Incomplete Information](https://mlsanity.com/paper/2211.00614/) (2022)
- [Reasoning over Hybrid Chain for Table-and-Text Open Domain QA](https://mlsanity.com/paper/2201.05880/) (2022)
- [DocHop-QA: Towards Multi-Hop Reasoning over Multimodal Document Collections](https://mlsanity.com/paper/2508.15851/) (2025)
- [Counterfactual Multihop QA: A Cause-Effect Approach for Reducing Disconnected Reasoning](https://mlsanity.com/paper/2210.07138/) (2022)
- [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)
- [Generating Chain-of-Thoughts with a Pairwise-Comparison Approach to Searching for the Most Promising Intermediate Thought](https://mlsanity.com/paper/2402.06918/) (2024)
- [Fact-driven Logical Reasoning for Machine Reading Comprehension](https://mlsanity.com/paper/2105.10334/) (2021)
- [ReasonChainQA: Text-based Complex Question Answering with Explainable Evidence Chains](https://mlsanity.com/paper/2210.08763/) (2022)
- [Rethinking Label Smoothing on Multi-hop Question Answering](https://mlsanity.com/paper/2212.09512/) (2022)
- [Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metrics](https://mlsanity.com/paper/2510.05137/) (2025)
- [Explaining the Road Not Taken](https://mlsanity.com/paper/2103.14973/) (2021)
- [Deductive Additivity for Planning of Natural Language Proofs](https://mlsanity.com/paper/2307.02472/) (2023)
- [Generative Context Pair Selection for Multi-hop Question Answering](https://mlsanity.com/paper/2104.08744/) (2021)

## Abstract (arXiv)

Multi-hop question answering requires models to gather information from different parts of a text to answer a question. Most current approaches learn to address this task in an end-to-end way with neural networks, without maintaining an explicit representation of the reasoning process. We propose a method to extract a discrete reasoning chain over the text, which consists of a series of sentences leading to the answer. We then feed the extracted chains to a BERT-based QA model to do final answer prediction. Critically, we do not rely on gold annotated chains or "supporting facts:" at training time, we derive pseudogold reasoning chains using heuristics based on named entity recognition and coreference resolution. Nor do we rely on these annotations at test time, as our model learns to extract chains from raw text alone. We test our approach on two recently proposed large multi-hop question answering datasets: WikiHop and HotpotQA, and achieve state-of-art performance on WikiHop and strong performance on HotpotQA. Our analysis shows the properties of chains that are crucial for high performance: in particular, modeling extraction sequentially is important, as is dealing with each candidate sentence in a context-aware way. Furthermore, human evaluation shows that our extracted chains allow humans to give answers with high confidence, indicating that these are a strong intermediate abstraction for this task.