# End-to-End Beam Retrieval for Multi-Hop Question Answering

arXiv: https://arxiv.org/abs/2308.08973 · HTML: https://mlsanity.com/paper/2308.08973/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 26 references that are in the map.
- First posted on arXiv 17 Aug 2023.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval](https://mlsanity.com/paper/2009.12756/) (2020)
- [Hierarchical Graph Network for Multi-hop Question Answering](https://mlsanity.com/paper/1911.03631/) (2019)
- [Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documents](https://mlsanity.com/paper/1911.00484/) (2019)
- [IIRC: A Dataset of Incomplete Information Reading Comprehension Questions](https://mlsanity.com/paper/2011.07127/) (2020)
- [Decomposing Complex Questions Makes Multi-Hop QA Easier and More Interpretable](https://mlsanity.com/paper/2110.13472/) (2021)
- [Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval](https://mlsanity.com/paper/2104.05883/) (2021)
- [Graph-free Multi-hop Reading Comprehension: A Select-to-Guide Strategy](https://mlsanity.com/paper/2107.11823/) (2021)
- [From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answering](https://mlsanity.com/paper/2205.11729/) (2022)
- [Reasoning over Hierarchical Question Decomposition Tree for Explainable Question Answering](https://mlsanity.com/paper/2305.15056/) (2023)
- [Rethinking Label Smoothing on Multi-hop Question Answering](https://mlsanity.com/paper/2212.09512/) (2022)
- [Analyzing the Effectiveness of the Underlying Reasoning Tasks in Multi-hop Question Answering](https://mlsanity.com/paper/2302.05963/) (2023)

## Built on by (most cited first, 30 of 35)

- [Sufficient Context: A New Lens on Retrieval Augmented Generation Systems](https://mlsanity.com/paper/2411.06037/) (2024)
- [Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answering](https://mlsanity.com/paper/2406.14891/) (2024)
- [Grounded Multi-Hop VideoQA in Long-Form Egocentric Videos](https://mlsanity.com/paper/2408.14469/) (2024)
- [SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers](https://mlsanity.com/paper/2504.00255/) (2025)
- [A Declarative System for Optimizing AI Workloads](https://mlsanity.com/paper/2405.14696/) (2024)
- [RAG-RL: Advancing Retrieval-Augmented Generation via RL and Curriculum Learning](https://mlsanity.com/paper/2503.12759/) (2025)
- [Making Long-Context Language Models Better Multi-Hop Reasoners](https://mlsanity.com/paper/2408.03246/) (2024)
- [Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models](https://mlsanity.com/paper/2410.01782/) (2024)
- [Researchy Questions: A Dataset of Multi-Perspective, Decompositional Questions for LLM Web Agents](https://mlsanity.com/paper/2402.17896/) (2024)
- [KGARevion: An AI Agent for Knowledge-Intensive Biomedical QA](https://mlsanity.com/paper/2410.04660/) (2024)
- [PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation](https://mlsanity.com/paper/2501.11551/) (2025)
- [MASTER: A Multi-Agent System with LLM Specialized MCTS](https://mlsanity.com/paper/2501.14304/) (2025)
- [LongFaith: Enhancing Long-Context Reasoning in LLMs with Faithful Synthetic Data](https://mlsanity.com/paper/2502.12583/) (2025)
- [GenDec: A robust generative Question-decomposition method for Multi-hop reasoning](https://mlsanity.com/paper/2402.11166/) (2024)
- [BeamAggR: Beam Aggregation Reasoning over Multi-source Knowledge for Multi-hop Question Answering](https://mlsanity.com/paper/2406.19820/) (2024)
- [Chain of Evidences and Evidence to Generate: Prompting for Context Grounded and Retrieval Augmented Reasoning](https://mlsanity.com/paper/2401.05787/) (2024)
- [MURRE: Multi-Hop Table Retrieval with Removal for Open-Domain Text-to-SQL](https://mlsanity.com/paper/2402.10666/) (2024)
- [RAG-based Question Answering over Heterogeneous Data and Text](https://mlsanity.com/paper/2412.07420/) (2024)
- [Rethinking All Evidence: Enhancing Trustworthy Retrieval-Augmented Generation via Conflict-Driven Summarization](https://mlsanity.com/paper/2507.01281/) (2025)
- [Beyond Chunks and Graphs: Retrieval-Augmented Generation through Triplet-Driven Thinking](https://mlsanity.com/paper/2508.02435/) (2025)
- [STOC-TOT: Stochastic Tree-of-Thought with Constrained Decoding for Complex Reasoning in Multi-Hop Question Answering](https://mlsanity.com/paper/2407.03687/) (2024)
- [SYMPHONY: Synergistic Multi-agent Planning with Heterogeneous Language Model Assembly](https://mlsanity.com/paper/2601.22623/) (2026)
- [Prompting Explicit and Implicit Knowledge for Multi-hop Question Answering Based on Human Reading Process](https://mlsanity.com/paper/2402.19350/) (2024)
- [Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training](https://mlsanity.com/paper/2511.07328/) (2025)
- [Sim-GPT: Text Similarity via GPT Annotated Data](https://mlsanity.com/paper/2312.05603/) (2023)
- [Gumbel Reranking: Differentiable End-to-End Reranker Optimization](https://mlsanity.com/paper/2502.11116/) (2025)
- [On Synthesizing Data for Context Attribution in Question Answering](https://mlsanity.com/paper/2504.05317/) (2025)
- [Momentum Posterior Regularization for Multi-hop Dense Retrieval](https://mlsanity.com/paper/2502.20399/) (2024)
- [Small Encoders Can Rival Large Decoders in Detecting Groundedness](https://mlsanity.com/paper/2506.21288/) (2025)
- [Multi-Hop Reasoning for Question Answering with Hyperbolic Representations](https://mlsanity.com/paper/2507.03612/) (2025)

## Abstract (arXiv)

Multi-hop question answering (QA) involves finding multiple relevant passages and step-by-step reasoning to answer complex questions, indicating a retrieve-and-read paradigm. However, previous retrievers were customized for two-hop questions, and most of them were trained separately across different hops, resulting in a lack of supervision over the entire multi-hop retrieval process and leading to poor performance in complicated scenarios beyond two hops. In this work, we introduce Beam Retrieval, an end-to-end beam retrieval framework for multi-hop QA. This approach models the multi-hop retrieval process in an end-to-end manner by jointly optimizing an encoder and two classification heads across all hops. Moreover, Beam Retrieval maintains multiple partial hypotheses of relevant passages at each step, expanding the search space and reducing the risk of missing relevant passages. To establish a complete QA system, we incorporate a supervised reader or a large language model (LLM). Experimental results demonstrate that Beam Retrieval achieves a nearly 50% improvement compared with baselines on challenging MuSiQue-Ans, and it also surpasses all previous retrievers on HotpotQA and achieves 99.9% precision on 2WikiMultiHopQA. Providing high-quality context, Beam Retrieval helps our supervised reader achieve new state-of-the-art performance and substantially improves the few-shot QA performance of LLMs.