MULTI-HOP QA

HiGraAgent: Dual-Agent Adaptive Reasoning over Hierarchical Knowledge Graph for Open Domain Multi-hop Question Answering (2026.findings-eacl)

Challenge:	Existing methods for weakly supervised multi-hop pretraining require costly human annotation.
Approach:	They propose a method for weakly supervised multi-hop retriever pretraining without human efforts by generating vector representations of complex questions and subquestion as weak supervision for pre-training.
Outcome:	The proposed method is effective and robust on limited data and computational resources.

Copied to clipboard

Hung Luu, Long S. T. Nguyen, Trung Pham, Hieu Pham, Tho Quan

Structured Data in NLP

Challenge:	Existing approaches to multi-hop question answering lack a robust and flexible approach to QA . prior work showed compositionality gap persists even for Large Language Models .
Approach:	They propose a framework that unifies graph-based retrieval with adaptive reasoning . HiGraAgent uses a hierarchical knowledge Graph with entity alignment .
Outcome:	The proposed framework outperforms the strongest graph-based method on hotpotQA, 2WikiMultihopQA, and MuSiQue.

Modeling Multi-hop Question Answering as Single Sequence Prediction (2022.acl-long)

Copied to clipboard

Semih Yavuz, Kazuma Hashimoto, Yingbo Zhou, Nitish Shirish Keskar, Caiming Xiong

Reasoning

Challenge:	Existing generative question answering models that leverage passage retrieval with a pre-trained transformer are not effective for multihop QA.
Approach:	They propose a generative approach that explicitly models the reasoning process to resolve the answer for multi-hop questions by encoding cross-passage interactions.
Outcome:	The proposed model improves on two multi-hop QA datasets and is interpretable.

Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering (2021.findings-acl)

Copied to clipboard

Weiwen Xu, Huihui Zhang, Deng Cai, Wai Lam

Multimodality

Challenge:	Existing approaches suffer from low confidence when retrieving evidence facts to fill the knowledge gap and lack transparent reasoning process.
Approach:	They propose a framework to exploit more valid facts while obtaining explainability for multi-hop question answering at web scale by dynamically constructing a semantic graph and reasoning over it.
Outcome:	The proposed framework surpasses existing approaches while maintaining high explainability on OpenBookQA and ARC-Challenge.

End-to-End Beam Retrieval for Multi-Hop Question Answering (2024.naacl-long)

Copied to clipboard

Jiahao Zhang, Haiyang Zhang, Dongmei Zhang, Liu Yong, Shen Huang

Prompt-based Conservation Learning for Multi-hop Question Answering (2022.coling-1)

Challenge:	Existing beam retrieval frameworks for multi-hop question answering were customized for two-hop questions and were poorly supervised.
Approach:	They propose an end-to-end beam retrieval framework for multi-hop question answering . they combine an encoder and two classification heads to optimize the retrieval process .
Outcome:	The proposed framework improves on MuSiQue-Ans and surpasses all previous retrievers on HotpotQA and achieves 99.9% precision on 2WikiMultiHopQA.

Copied to clipboard

Zhenyun Deng, Yonghua Zhu, Yang Chen, Qianqian Qi, Michael Witbrock, Patricia Riddle

Responsible & Trustworthy NLP

Challenge:	Existing multi-hop QA methods fail to answer a large fraction of sub-questions even if their parent questions are answered correctly.
Approach:	They propose a Prompt-based Conservation Learning framework that acquires new knowledge from multi-hop QA tasks while conserving old knowledge learned on single-hop tasks.
Outcome:	The proposed framework acquires new knowledge from multi-hop QA tasks while conserving old knowledge learned on single-hop tasks, mitigating forgetting.

Collaborative Chain-of-Agents for Parametric-Retrieved Knowledge Synergy (2026.acl-long)

Copied to clipboard

Yi Jiang, Sendong Zhao, Jianbo Li, Haochun Wang, Lizhe Zhang, Yan Liu, Bing Qin

Don’t Forget the Base Retriever! A Low-Resource Graph-based Retriever for Multi-hop Question Answering (2025.emnlp-industry)

Challenge:	Existing RAG methods focus on external retrieval, while ignoring the rich content of the model.
Approach:	They propose a framework that enhances explicit synergy over parametric and retrieved knowledge by integrating external retrieval components into the input context of the LLMs.
Outcome:	The proposed framework enhances explicit synergy over parametric and retrieved knowledge.

Copied to clipboard

Andre Melo, Enting Chen, Pavlos Vougiouklis, Chenxin Diao, Shriram Piramanayagam, Ruofei Lai, Jeff Z. Pan

Structured Data in NLP

Challenge:	Existing GraphRAG approaches to multi-hop question answering rely on expensive LLM calls.
Approach:	They propose a lightweight, low-resource, multi-step graph-based retriever for multi-hop QA that performs multi- step retrieval in a few hundred milliseconds.
Outcome:	The proposed retriever outperforms conventional retrievers on multi-hop QA datasets and shows strong potential as a base retriever within multi-step agentic frameworks.

Calibrating Trust of Multi-Hop Question Answering Systems with Decompositional Probes (2022.findings-emnlp)

Copied to clipboard

Kaige Xie, Sarah Wiegreffe, Mark Riedl

Natural Language Interfaces

Challenge:	Recent work in multi-hop QA has shown that performance can be boosted by decomposing questions into simpler, single-hop questions.
Approach:	They propose to decompose multi-hop questions into simpler, single-hop ones to create explanations by probing a neural QA model with them.
Outcome:	The proposed approach can be used to generate explanations by probing a neural QA model with them.

BELLE: A Bi-Level Multi-Agent Reasoning Framework for Multi-Hop Question Answering (2025.acl-long)

Copied to clipboard

Taolin Zhang, Dongyang Li, Qizhou Chen, Chengyu Wang, Xiaofeng He

Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering (D19-1)

Challenge:	Existing studies on multi-hop question answering employ specific methods regardless of question types . complexity of multihop question answerrs often exceeds knowledge boundaries of LLMs .
Approach:	They propose a framework that uses chain-of-thought prompting to prompt LLMs to answer multi-hop questions.
Outcome:	The proposed framework outperforms baseline models in multi-hop QA scenarios.

Copied to clipboard

Vikas Yadav, Steven Bethard, Mihai Surdeanu

Low-Resource NLP

Challenge:	Arras et al., 2017) suggest an unsupervised strategy for the selection of justification sentences for multi-hop question answering (QA) .
Approach:	They propose an unsupervised strategy for the selection of justification sentences for multi-hop question answering that maximizes the relevance of the selected sentences, minimizes overlap between selected facts, and maximizes coverage of both question and answer.
Outcome:	The proposed strategy improves state-of-the-art supervised QA model on two multi-hop QA datasets: AI2’s Reasoning Challenge (ARC) and Multi-Sentence Reading Comprehension (MultiRC).

Do Multi-Hop Question Answering Systems Know How to Answer the Single-Hop Sub-Questions? (2021.eacl-main)

Copied to clipboard

Yixuan Tang, Hwee Tou Ng, Anthony Tung

TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph (2021.emnlp-main)

Challenge:	Existing models fail to answer a large portion of sub-questions . Existing systems have achieved super-human performance .
Approach:	They propose to use a neural decomposition model to generate sub-questions for a multi-hop question and extract the corresponding sub-answers.
Outcome:	The proposed model is based on a hotpotQA dataset with a multi-hop question and sub-answers.

Copied to clipboard

Jiaxin Shi, Shulin Cao, Lei Hou, Juanzi Li, Hanwang Zhang

Explainability & Interpretability in NLP

Challenge:	Existing models infer the answer by predicting the sequential relation path or aggregating the hidden graph features.
Approach:	They propose a model which jumps between entities at multiple steps . they demonstrate that TransferNet surpasses state-of-the-art models by a large margin .
Outcome:	The proposed model surpasses state-of-the-art models on MetaQA and on other datasets.

StepKE: Stepwise Knowledge Editing for Multi-Hop Question Answering (2025.findings-emnlp)

Copied to clipboard

Jaewook Lee, Dahyun Jung, Heuiseok Lim

A STEP towards Interpretable Multi-Hop Reasoning:Bridge Phrase Identification and Query Expansion (2022.lrec-1)

Challenge:	Existing knowledge editing methods overlook interplay with pre-existing knowledge, leading to inconsistent edit propagation.
Approach:	stepKE integrates edited and existing knowledge for coherent multi-hop reasoning . stepKE decomposes multi-step questions into sequential single-hop sub-questions .
Outcome:	Experiments show that StepKE generates more accurate and consistent responses than baselines.

Copied to clipboard

Fan Luo, Mihai Surdeanu

Momentum Posterior Regularization for Multi-hop Dense Retrieval (2025.coling-main)

Challenge:	Identifying bridge phrases remains one of the challenges for multi-hop question answering .
Approach:	They propose an unsupervised method for the identification of bridge phrases in multi-hop question answering . they construct a graph of noun phrases from the question and available context .
Outcome:	The proposed method improves all downstream components in a multi-hop QA system.

Copied to clipboard

Zehua Xia, Yuyang Wu, Yiyun Xia, Cam Tu Nguyen

Semantic Text Processing

Challenge:	Current methods for knowledge distillation in one-time retrieval are ineffective for multi-hop QA . posterior information is often defined as the response, which may not connect to the query without intermediate retrieval .
Approach:	They propose to distill knowledge from a posterior retrieval into a prior retrieval for multi-hop QA . they propose to use momentum moving average method to update posterior information along with prior retrievals .
Outcome:	Experiments on HotpotQA and StrategyQA show that MoPo outperforms baselines in retrieval and downstream QA tasks.

ReadOnce Transformers: Reusable Representations of Text for Transformers (2021.acl-long)

Copied to clipboard

Shih-Ting Lin, Ashish Sabharwal, Tushar Khot

Semantic Text Processing

Challenge:	ReadOnce Transformers is a task-independent, task-dependent, and compressed representation of text.
Approach:	They propose a transformer-based model that can build an information-capturing, task-independent, and compressed representation of text.
Outcome:	The proposed model can build an information-capturing, task-independent, and compressed representation of text.

Generative Context Pair Selection for Multi-hop Question Answering (2021.emnlp-main)

Copied to clipboard

Dheeru Dua, Cicero Nogueira dos Santos, Patrick Ng, Ben Athiwaratkun, Bing Xiang, Matt Gardner, Sameer Singh

Reasoning

Challenge:	Recent studies have shown that discriminative training results in models that exploit these underlying biases to achieve a better held-out performance, without learning the right way to reason.
Approach:	They propose a generative context selection model for multi-hop QA that reasons about how the given question could have been generated given a context pair and not just independent contexts.
Outcome:	The proposed model outperforms the state-of-the-art model on hotpotQA while being comparable to the state of the art answering performance on adversarial held-out set.

Generalizable LLM Learning of Graph Synthetic Data with Post-training Alignment (2026.findings-acl)

Copied to clipboard

Yizhuo Zhang, Heng Wang, Shangbin Feng, Zhaoxuan Tan, Xinyun Liu, Yulia Tsvetkov

Structured Data in NLP

Challenge:	Existing research has focused on enhancing graph reasoning capabilities of LLMs by supervised fine-tuning on synthetic graph data.
Approach:	They propose to unlock generalizable learning of graph with post-training alignment with synthetic graph data by aligning off-the-shelf LLMs and LLM fine-tuned on synthetic graphs.
Outcome:	The proposed algorithm improves on synthetic graph problems and out-of-domain tasks with implicit graph structures.

Fine-Tuning and Prompt Optimization: Two Great Steps that Work Better Together (2024.emnlp-main)

Copied to clipboard

Dilara Soylu, Christopher Potts, Omar Khattab

Is Multihop QA in DiRe Condition? Measuring and Reducing Disconnected Reasoning (2020.emnlp-main)

Challenge:	Recent work shows the potential of building more powerful Natural Language Processing systems by composing multiple skills of LMs into pipelines.
Approach:	They propose to combine weight and prompt optimization strategies to optimize a modular LM pipeline.
Outcome:	The proposed strategies outperform optimizing weights and prompts alone by 60% and 6% on average across LMs and tasks.

Copied to clipboard

Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, Ashish Sabharwal

Reasoning

Challenge:	Existing models exploit dataset artifacts to produce correct answers without connecting information across multiple facts.
Approach:	They formalize disconnected reasoning across subsets of supporting facts to reduce disconnected reasoning . they propose an automatic transformation of existing datasets that reduces disconnected reasoning.
Outcome:	The proposed model-agnostic probe reduces disconnected reasoning in a reading comprehension setting.

Resource-Friendly Dynamic Enhancement Chain for Multi-Hop Question Answering (2025.findings-acl)

Copied to clipboard

Binquan Ji, Haibo Luo, YifeiLu YifeiLu, Lei Hei, Jiaqi Wang, Tingjing Liao, Wang Lingyu, Shichao Wang, Feiliang Ren

Natural Language Interfaces

Challenge:	Existing approaches to solve multi-hop question answering challenges require multiple rounds of retrieval and iterative generation.
Approach:	They propose a framework that decomposes complex questions into coherent subquestions . it then iteratively refines these subquests through context-aware rewriting to generate effective query formulations.
Outcome:	The proposed framework performs on par with or surpasses state-of-the-art benchmarks while significantly reducing token consumption.

Style-Compress: An LLM-Based Prompt Compression Framework Considering Task-Specific Styles (2024.findings-emnlp)

Copied to clipboard

Xiao Pu, Tianxing He, Xiaojun Wan

Few-shot Reranking for Multi-hop QA via Language Model Prompting (2023.acl-long)

Challenge:	Prompt compression reduces inference time and costs while maintaining informativeness for different usage scenarios.
Approach:	They propose a framework that adapts a smaller language model to compress prompts for a larger model on a new task without additional training.
Outcome:	The proposed framework outperforms two baseline models in four tasks . iteratively generates and selects effective compressed prompts as task-specific demonstrations .

Copied to clipboard

Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, Lu Wang

StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization (2025.emnlp-main)

Challenge:	Existing methods for multi-hop QA with open-domain questions require a large number of labeled question-document pairs for retrieval.
Approach:	They propose a language-based prompt for multi-hop path reranking that relies on language model prompting to generate a relevance score between a question and the path.
Outcome:	The proposed method yields strong retrieval performance on HotpotQA with only 128 training examples compared to state-of-the-art methods trained on thousands of examples.

Copied to clipboard

Xuhui Zheng, Kang An, Ziliang Wang, Yuhang Wang, Yichao Wu

Prompting Explicit and Implicit Knowledge for Multi-hop Question Answering Based on Human Reading Process (2024.lrec-main)

Challenge:	Recent work has demonstrated unprecedented capabilities in sophisticated linguistic comprehension and generative tasks.
Approach:	They propose a framework for search LLMs that trains with step-wise proximal policy optimization method to improve QA performance.
Outcome:	The proposed framework outperforms global-reward benchmarks on multi-hop QA with a stepwise proximal policy optimization method and richer and more detailed intermediate search rewards and token-level process supervision.

Copied to clipboard

Guangming Huang, Yunfei Long, Cunjin Luo, Jiaxing Shen, Xia Sun

S2G-RAG: Structured Sufficiency and Gap Judging for Iterative Retrieval-Augmented QA (2026.acl-long)

Challenge:	Existing studies have not explored the link between PLMs’ pre-training-based knowledge and input passages.
Approach:	They propose a framework that uses prompts to connect explicit and implicit knowledge to elicit type-specific reasoning via prompts, a form of implicit knowledge.
Outcome:	The proposed model performs comparable to the state-of-the-art on HotpotQA.

Copied to clipboard

Minghan Li, Junjie Zou, Xinxuan Lv, Chao Zhang, Guodong Zhou

Attention Basin: Why Contextual Position Matters in Large Language Models (2026.acl-long)

Challenge:	Retrieval-augmented generation grounds language models in external evidence, but multi-hop question answering remains difficult . iterative pipelines must control what to retrieve next and when evidence is adequate.
Approach:	They propose an iterative framework with an explicit controller, S2G-Judge . they map structured gap items into the next retrieval query to produce stable retrieval trajectories .
Outcome:	Experiments on TriviaQA, HotpotQA, and 2WikiMultiHopQA show that S2G-RAG improves multi-hop QA performance and robustness under multi-turn retrieval.

Copied to clipboard

Zihao Yi, Zhenqing Ling, Delong Zeng, Haohao Luo, Zhe Xu, Wei Liu, Jian Luan, Wanxia Cao, Ying Shen

Semantic Text Processing

Challenge:	Large Language Models (LLMs) are sensitive to the contextual position of information in input.
Approach:	They introduce Attention-Driven Reranking (AttnRank) which estimates a model’s intrinsic positional attention preferences using a small calibration set and reorders retrieved documents or few-shot examples to align the most salient content with these high-attention positions.
Outcome:	Experiments on multi-hop QA and few-shot in-context learning tasks show that AttnRank achieves substantial improvements across 10 large language models of varying architectures and scales, without modifying model parameters or training procedures.

SmartAD: Capacity-Aligned Agent Distillation for Small Language Models (2026.findings-acl)

Copied to clipboard

Guokai Tang, Feng Zhao