♫ MuSiQue: Multihop Questions via Single-hop Question Composition
Open accessThe DOI matches its Crossref record; 55 of the 55 references it cites were found in a registry or an index.
Abstract
Multihop reasoning remains an elusive goal as existing multihop benchmarks are known to be largely solvable via shortcuts. Can we create a question answering (QA) dataset that, by construction, requires proper multihop reasoning? To this end, we introduce a bottom–up approach that systematically selects composable pairs of single-hop questions that are connected, that is, where one reasoning step critically relies on information from another. This bottom–up methodology lets us explore a vast space of questions and add stringent filters as well as other mechanisms targeting connected reasoning. It provides fine-grained control over the construction process and the properties of the resulting k-hop questions. We use this methodology to create MuSiQue-Ans, a new multihop QA dataset with 25K 2–4 hop questions. Relative to existing datasets, MuSiQue-Ans is more difficult overall (3× increase in human–machine gap), and harder to cheat via disconnected reasoning (e.g., a single-hop model has a 30-point drop in F1). We further add unanswerable contrast questions to produce a more stringent dataset, MuSiQue-Full. We hope our datasets will help the NLP community develop models that perform genuine multihop reasoning.1
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The majority of existing QA datasets (Rajpurkar et al., 2018; Yang et al., 2018; Trivedi et al., 2022) are designed to answer questions based on short passages.”
From RULER: What's the Real Context Size of Your Long-Context Language Models? (2024) · cites this paper as Trivedi et al., 2022
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Multi-hop QA benchmarks (HotpotQA [52], 2WikiMultiHopQA [16], MuSiQue [42]) and long-document QA such as QuALITY [33] test compositional retrieval and reasoning over a fixed corpus.”
From MemGym: a Long-Horizon Memory Environment for LLM Agents (2026) · cites this paper as [42]
The cited source says what the claim attributes to it.
In the citing paper
“Text and multi-hop QA emphasize evidence tracking and state bookkeeping over intermediate facts (Ho et al., 2020; Trivedi et al., 2022).”
From A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents (2026) · cites this paper as Trivedi et al., 2022
In the citing paper
“RAG is predominantly applied to augment LLMs with large, externally sourced context for individual inference tasks, exemplified by classical multi-hop and knowledge-intensive benchmarks such as HotpotQA (Yang et al., 2018), 2WikiMQA (Ho et al., 2020), and MuSiQue (Trivedi et al., 2022).”
From Memory in the Age of AI Agents (2025) · cites this paper as Trivedi et al., 2022
In the citing paper
“Consequently, a more practical (though not perfectly separable) distinction lies in the task domain . RAG is predominantly applied to augment LLMs with large, externally sourced context for individual inference tasks, exemplified by classical multi-hop and knowledge-intensive benchmarks such as HotpotQA (Yang et al., 2018), 2WikiMQA (Ho et al., 2020), and MuSiQue (Trivedi et al., 2022). By contra”
From Memory in the Age of AI Agents (2025) · cites this paper as Trivedi et al., 2022
1 more claim about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2019) · arXiv · doi:10.48550/arxiv.1910.13461 · Cited by 8,816
Transformers: State-of-the-Art Natural Language Processing
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., et al. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations · doi:10.18653/v1/2020.emnlp-demos.6 · Cited by 8,741
SQuAD: 100,000+ Questions for Machine Comprehension of Text
Rajpurkar, P., Zhang, J., Lopyrev, K., & Liang, P. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1264 · Cited by 6,208 · cited 1×
“We start with 2017K single-hop questions from 5 datasets (SQuAD (Rajpurkar et al., 2016), Natural Questions (Kwiatkowski et al.”
MethodLongformer: The Long-Document Transformer
Beltagy, I., Peters, M. E., & Cohan, A. (2020) · arXiv · doi:10.48550/arxiv.2004.05150 · Cited by 2,281
Know What You Don't Know: Unanswerable Questions for SQuAD
Rajpurkar, P., Jia, R., & Liang, P. (2018) · arXiv · doi:10.48550/arxiv.1806.03822 · Cited by 2,242
Research works printed but not linked: 2
- ElSahar, 2018, T-REx: A large scale alignment of natural language with knowledge base triples
- Talmor, 2021, MultiModalQA: Complex question answering over text, tables and images, 10.18653/v1/N18-1059 · DOI · Paper page
Cited by
Items 101–200 of 381
AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents
Anokhin, P., Semenov, N., Sorokin, A., Evseev, D., Kravchenko, A., Burtsev, M., & Burnaev, E. (2024) · arXiv · doi:10.48550/arxiv.2407.04363 · Cited by 8
“ArigGraph (GPT-4o-mini) showed weaker performance on Musique, but outperformed GraphRAG on HotpotQA.”
GARAG: A General adaptive question-answering system based on RAG
Wei, Z., Huang, D., Zhang, J., Song, C., Zhang, S., Zhang, J., Li, Z., Jiang, K., Li, R., & Duan, Q. (2024) · ICCBD · doi:10.1145/3695080.3695156 · Cited by 4
KnowTrace: Bootstrapping Iterative Retrieval-Augmented Generation with Structured Knowledge Tracing
Li, R. L., Dai, Q., Zhang, Z., Chen, X., Dong, Z., & Wen, J.-R. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3711896.3737015 · Cited by 20
AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoning
Xin, A., Liu, J., Yao, Z., Lee, Z., Cao, S., Hou, L., & Li, J. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3711896.3736849 · Cited by 17
WADSeg: Exploiting weak attention associations for enhanced knowledge segmentation in RAG
Guo, T., Wang, C., Yang, Q., Tang, J., Liu, Y., & Wen, Y. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.129297 · Cited by 7
R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning
Yuan, L., Luo, Q., Li, X., Li, B., Cheng, Q., Wang, B., Zheng, Y., Wang, Y., Yin, Z., & Qiu, X. (2025) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2025.findings-emnlp.554 · Cited by 15
Revisiting Text Ranking in Deep Research
Meng, C., Ou, L., MacAvaney, S., & Dalton, D. J. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3808557 · Cited by 11
Misra, K., dos Santos, C. N., & Shakeri, S. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.62 · Cited by 7
A Comprehensive Evaluation of Tool-Assisted Generation Strategies
Jacovi, A., Caciularu, A., Herzig, J., Aharoni, R., Bohnet, B., & Geva, M. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.926 · Cited by 10
Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answering
Wang, Z., Thomason, J., & Jia, R. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.547 · Cited by 14
Pre-training Language Models for Comparative Reasoning
Yu, M., Zhang, Z., Yu, W., & Jiang, M. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.763 · Cited by 13
CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion
Yao, J., Li, H., Liu, Y., Ray, S., Cheng, Y., Zhang, Q., Du, K., Lu, S., & Jiang, J. (2026) · ACM Transactions on Computer Systems · doi:10.1145/3790254 · Cited by 3
Single Sequence Prediction over Reasoning Graphs for Multi-hop QA
Ramesh, G., Sreedhar, M. N., & Hu, J. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.642 · Cited by 3
Guo, T., Wang, C., Liu, Y., Tang, J., Li, P., Sai, X., Yang, Q., Gao, X., Li, Z., & Wen, Y. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130931 · Cited by 6
Wei, Q., Ning, H., Han, C., & Ding, J. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.131932 · Cited by 6
Yuan, M., Wang, T., & Qian, Y. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-01028-3 · Cited by 3
Beyond decomposition: Hierarchical dependency management in multi‐document question answering
Zheng, X., Li, Z., Chen, Q., & Zhang, Y. (2024) · Journal of the Association for Information Science and Technology · doi:10.1002/asi.24971 · Cited by 3
LLM-based Search Assistant with Holistically Guided MCTS for Intricate Information Seeking
Ren, R., Wang, Y., Li, J., Jiang, J., Zhao, W. X., Wang, W., & Chua, T. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3730025 · Cited by 11
CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion
Yao, J., Li, H., Liu, Y., Ray, S., Cheng, Y., Zhang, Q., Du, K., Lu, S., & Jiang, J. (2024) · arXiv · doi:10.48550/arxiv.2405.16444 · Cited by 3
Self-Critique Guided Iterative Reasoning for Multi-hop Question Answering
Chu, Z., Fan, H., Chen, J., Wang, Q., Yang, M., Liang, J., Wang, Z., Li, H., Tang, G., Liu, M., et al. (2025) · Findings of the Association for Computational Linguistics: ACL 2025 · doi:10.18653/v1/2025.findings-acl.123 · Cited by 2
From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
Gutiérrez, B. J., Shu, Y., Qi, W., Zhou, S., & Su, Y. (2025) · arXiv · doi:10.48550/arxiv.2502.14802 · Cited by 2
“We randomly collect 1 , 000 queries from MuSiQue , 2WikiMultihopQA , and HotpotQA following HippoRAG (Guti´errez et al., 2024), all requiring multi-passage reasoning.”
InfluentialLi, S., Du, Y., & Li, M. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3730203 · Cited by 3
Zhang, W., Zhang, K., Li, T., & Deng, W. (2025) · Inventions · doi:10.3390/inventions10050074 · Cited by 2
Kyoung, M., Lim, J.-H., & Kim, Y. (2025) · IEEE Access · doi:10.1109/access.2025.3617449 · Cited by 3
Explainable Multi-Hop Question Answering: A Rationale-Based Approach
Han, K., Jang, Y., & Kim, H. (2025) · Big Data and Cognitive Computing · doi:10.3390/bdcc9110273 · Cited by 3
NovelHopQA: Diagnosing Multi-Hop Reasoning Failures in Long Narrative Contexts
Gupta, A., Zhu, K., Sharma, V., O’Brien, S., & Lu, M. (2025) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2025.emnlp-main.1328 · Cited by 15
Retrieving on a topic graph for long document question answering
Chen, S., Liang, B., Yu, Y., Wong, K., Wang, H., & Xu, R. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.132447 · Cited by 4
FoRKER: Focused reasoner with knowledge editing and self-reflection
Zhang, C., Li, H., Wang, C., Zhou, Y., & Peng, Y. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.129771 · Cited by 2
M o N a C o : More Natural and Complex Questions for Reasoning Across Dozens of Documents
Wolfson, T., Trivedi, H. K., Geva, M., Goldberg, Y., Roth, D., Khot, T., Sabharwal, A., & Tsarfaty, R. (2026) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl.a.64 · Cited by 20
Self-citationTesting Explainability of Chain of Thought for Large Language Models
Chen, H., Zhao, Z., Shuai, Z., & Xuan, J. (2026) · Applied Sciences · doi:10.3390/app16073112 · Cited by 2
SA-RAG: Structured and adaptive retrieval-augmented generation for multi-hop question answering
Dang, M., Geng, S., Xu, Y., Wang, F., & Cui, L. (2026) · Neural Networks · doi:10.1016/j.neunet.2026.109201 · Cited by 2
Tail-Aware Adaptive-k: Query-Adaptive Context Selection for Retrieval-Augmented Generation
Song, Z., Fang, J., Li, K., Xia, T., & Wang, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37667-1_12 · Cited by 2
Trust Within? Seek Beyond? Knowledge Boundary Aware Policy Optimization for Agentic Search
Feng, T., Jiang, X., Hu, X., Zhang, Y., Tao, Z., Zhang, W., Liu, B., Jiang, W., & Wu, C. (2026) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2026.acl-long.1276 · Cited by 8
Question-Adaptive Graph Learning for Multi-hop Retrieval Augmented Generation
Yan, Y., Zhang, P., Liu, Z., Wang, H., Bian, Y., Li, W., & Hao, X. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809693 · Cited by 3
RouteGoT: Node-Adaptive Routing for Cost-Efficient Graph of Thoughts Reasoning
Liu, Y., Wang, R., Chu, Y., Hao, B., Lin, Y., Liu, S., & Shao, M. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818056 · Cited by 2
Multi-perspective thought navigation for source-free entity linking
Peng, B., He, W. P., Chen, B., Villavicencio, A., & Wu, C. (2024) · Pattern Recognition Letters · doi:10.1016/j.patrec.2023.12.020 · Cited by 2
Complex Reasoning in Natural Languag
Zhao, W., Geva, M., Lin, B. Y., Yasunaga, M., Madaan, A., & Yu, T. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-tutorials.2 · Cited by 11
Pleias 1.0: the First Ever Family of Language Models Trained on Fully Open Data
Langlais, P.-C., Chizhov, P., Nee, M., Hinostroza, C. R., Delsart, M., Girard, I., Stasenko, A., & Yamshchikov, I. P. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.08.241 · Cited by 5
Self-Consistency Falls Short! The Adverse Effects of Positional Bias on Long-Context Problems
Byerly, A., & Khashabi, D. (2026) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl.a.625 · Cited by 12
Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
Zhou, H., Chen, Y., Guo, S., Yan, X., Lee, K. H., Wang, Z., Lee, K. Y., Zhang, G., Shao, K., Yang, L., et al. (2025) · arXiv · doi:10.48550/arxiv.2508.16153 · Cited by 2
“Specifically, MusiQue (Trivedi et al., 2022), Bamboogle (Press et al., 2022), and PopQA (Mallen et al., 2022) are selected as OOD datasets due to their distinct question styles and information distributions, while NQ (Kwiatkowski et al., 2019), TQ (Joshi et al., 2017), HotpotQA (Yang et al., 2018),…”
InfluentialFact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation
Krishna, S., Krishna, K., Mohananey, A., Schwarcz, S., Stambler, A., Upadhyay, S., & Faruqui, M. (2024) · arXiv · doi:10.48550/arxiv.2409.12941 · Cited by 1
Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topics
Du, Y., Huang, W., Zheng, D., Wang, Z., Montella, S., Lapata, M., Wong, K.-F., & Pan, J. Z. (2025) · arXiv · doi:10.48550/arxiv.2505.00675 · Cited by 1
Gated Delta Networks: Improving Mamba2 with Delta Rule
Yang, S., Kautz, J., & Hatamizadeh, A. (2024) · arXiv · doi:10.48550/arxiv.2412.06464 · Cited by 1
Analyzing Retrieval Scaling in RAG Systems for Complex QA Benchmarks
Mosquera, J. S. R., & Manrique, R. (2025) · SN Computer Science · doi:10.1007/s42979-025-04302-9 · Cited by 1
Turkuaz-RAG — A Turkish Multi-Context Retrieval Benchmark
Uysal, E. S., & Amasyalı, M. F. (2025) · Innovations in Intelligent Systems and Applications Conference (ASYU) · doi:10.1109/asyu67174.2025.11208268 · Cited by 1
Huang, S. L., & Cheng, J. (2025) · International Conference on Communication Technology and Information Technology (ICCTIT) · doi:10.1109/icctit68197.2025.11406504 · Cited by 1
Borovina, R., & Mišić, M. (2026) · International Symposium INFOTEH-JAHORINA (INFOTEH) · doi:10.1109/infoteh68759.2026.11477693 · Cited by 1
Uncertainty Guided Global Memory Improves Multi-Hop Question Answering
Sagirova, A., & Burtsev, M. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.262 · Cited by 1
Tackling the Length Barrier: Dynamic Context Browsing for Knowledge-Intensive Task
Qian, H., Liu, Z., Zhang, P., Mao, K., Zhou, Y., Chen, X., & Dou, Z. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3690624.3709240 · Cited by 1
Tan, T., Qian, Y., Lv, A., Lin, H., Wu, S., Wang, Y., Wang, F., Wu, J., Lu, X., & Yan, R. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3696410.3714795 · Cited by 3
ShortPathQA: A Dataset for Controllable Fusion of Large Language Models with Knowledge Graphs
Salnikov, M., Sakhovskiy, A., Nikishina, I., Usmanova, A., Kraft, A., Möller, C., Banerjee, D., Huang, J., Jiang, L., Abdullah, R., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-97141-9_7 · Cited by 1
AdaGCRAG: Adaptive Graph-Chunk Retrieval for Lightweight RAG
Zhang, Y., Xu, Z., Huo, D., Guo, X., Zhou, Q., & Zhang, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-09527-5_32 · Cited by 2
Towards Complex Question Answering in Polish Language
Wojtasik, K., Domagała, A., Oleksy, M., & Piasecki, M. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-09318-9_18 · Cited by 2
DAVIS: Planning Agent with Knowledge Graph-Powered Inner Monologue
Dinh, M. P., Yankoski, M. G., Syed, M., & Ford, T. W. (2025) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2025.findings-emnlp.895 · Cited by 4
Tree-of-Quote Prompting Improves Factuality and Attribution in Multi-Hop and Medical Reasoning
Xu, J., Li, Y., Zhang, Z., Luk, A., Jobanputra, M., Oza, S., Murray, A., Kasula, M. R., Parker, A., & Eyre, D. W. (2025) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2025.emnlp-main.285 · Cited by 6
Jin, Z., Yi, Z., Tu, Z., & Chu, D. (2025) · Service Oriented Computing and Applications · doi:10.1007/s11761-025-00481-8 · Cited by 1
Relative Performance Bandits: An Adaptive RAG Framework with Reward-Aware Exploration
Dai, Y., Li, J., & Li, B. (2025) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads67057.2025.11322957 · Cited by 1
Liu, Z., Huang, P., Xu, Z., Li, X., Liu, S., Peng, C., Xin, H., Yan, Y., Wang, S., Han, X., et al. (2026) · AI Open · doi:10.1016/j.aiopen.2026.02.002 · Cited by 11
Wei, Y., Li, X., Huang, Z., Lin, Z., & Zhang, N. (2026) · Computers in Industry · doi:10.1016/j.compind.2026.104462 · Cited by 1
Augmenting RAG with nonnegative matrix factorization-driven semantic chunking in embedding space
Abdolinejad, F., & Eftekhari, M. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-026-08370-3 · Cited by 1
Reasoning-guided structured planning and search in large language models
Shen, Y., & Shi, W. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.104732 · Cited by 4
Li, W., Wang, J., Yu, L.-C., & Zhang, X. (2026) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2026.3677587 · Cited by 1
DaPT: A Dual-Path Framework for Multilingual Multi-hop Question Answering
Wang, Y.-L., Fan, Y.-C., Li, J.-Y., Zhu, Z.-M., Mu, Y.-Y., He, Q.-Z., Xiao, T., & Zhu, J.-B. (2026) · IEEE International Conference on Acoustics, Speech, and Signal Processing · doi:10.1109/icassp55912.2026.11462873 · Cited by 2
KGCRAG: An Adaptive Community Detection Framework for Robust Graph-Enhanced RAG
Fang, W., Chen, G., Yuan, C., Lin, R., Tang, S., & Tang, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-0369-7_36 · Cited by 1
AttnTrace: Contextual Attribution of Prompt Injection and Knowledge Corruption
Wang, Y., Geng, R., Chen, Y., & Jia, J. (2026) · IEEE Symposium on Security and Privacy (S&P) · doi:10.1109/sp63933.2026.00198 · Cited by 17
No Shortcuts to Culture: Indonesian Multi-hop Question Answering for Complex Cultural Understanding
Permadi, V. A., Tan, X., Moosavi, N. S., & Αλέτρας, Ν. (2026) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl.a.726 · Cited by 2
STRIDE: Strategic Iterative Decision-Making for Retrieval-Augmented Multi-Hop Question Answering
Chen, W., Zhao, L., Zheng, Z., Hou, H., & Xu, T. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809703 · Cited by 4
SmartSearch: Process Reward-Guided Query Refinement for Search Agents
Wen, T., Dong, G., & Dou, Z. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809700 · Cited by 18
Retrieval Augmented Tree of Thoughts
Liu, X., & Liu, J. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-9434-8_36 · Cited by 1
Zhao, P., Zhang, Z., & Liu, B. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-9431-7_4 · Cited by 1
Graph-Induced Transformers for Efficient Multi-Hop Question Answering
Hong, G., Kim, J.-H., Kang, J., & Myaeng, S.-H. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.702 · Cited by 6
FinePrompt: Unveiling the Role of Finetuned Inductive Bias on Compositional Reasoning in GPT-4
Kim, J.-H., Hong, G., Myaeng, S.-H., & Whang, J. J. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.245 · Cited by 4
Understanding the Impact of Dataset Characteristics on RAG based Multi-hop QA PerformancePreprint
Aksoy, N., Güven, Z. A., & Ünalır, M. O. (2025) · Research Square · doi:10.21203/rs.3.rs-6968562/v1 · Cited by 1
End-to-End Beam Retrieval for Multi-Hop Question Answering
Zhang, J., Zhang, H., Zhang, D., Liu, Y., & Huang, S. (2023) · arXiv · doi:10.48550/arxiv.2308.08973 · Cited by 1
TaSR-RAG: Taxonomy-guided Structured Reasoning for Retrieval-Augmented Generation
Sun, J., Xie, Y., Shi, J., Wang, S., & Han, J. (2026) · arXiv · doi:10.48550/arxiv.2603.09341
“To investigate complex reasoning, we include several multi-hop datasets: HotpotQA [28], 2Wiki-MultiHopQA [5], MuSiQue [24], and Bamboogle [16].”
Multi-agent discussion gains less when dissent is withheld
Mansuri, C. S., Wang, X., Li, M., Acton, B., Eckardt, R., Patel, D., & Kojaku, S. (2026) · arXiv · doi:10.48550/arxiv.2609.38324 · Cited by 1
“On MuSiQue the relation is unclear (Fig.”
InfluentialMemGym: a Long-Horizon Memory Environment for LLM Agents
Xu, W., Wang, Y., Mei, K., Liang, K., Wang, Z., Jin, M., Zhang, H., Zhang, S.-X., Hua, W., Sahu, S., et al. (2026) · arXiv · doi:10.48550/arxiv.2605.20833 · Cited by 11
“Multi-hop QA benchmarks (HotpotQA [52], 2WikiMultiHopQA [16], MuSiQue [42]) and long-document QA such as QuALITY [33] test compositional retrieval and reasoning over a fixed corpus.”
RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory
Liu, J., Kong, Z., Yang, C., Yang, F., Li, T., Dong, P., Nanjekye, J., Tang, H., Yuan, G., Niu, W., et al. (2025) · arXiv · doi:10.48550/arxiv.2508.04903 · Cited by 37
“Figure 3 illustrates the comparison of average run-time (in seconds) across three datasets— HotPotQA , MuSiQue , and 2wikimultihop —for three routing methods: Full-Context , Static Routing , and RCR-router .”
InfluentialWideSearch: Benchmarking Agentic Broad Info-Seeking
Wong, R., Wang, J., Zhao, J., Chen, L., Gao, Y., Zhang, L., Zhou, X., Wang, Z., Xiang, K., Zhang, G., et al. (2025) · arXiv · doi:10.48550/arxiv.2508.07999
“The subsequent development of multi-hop QA datasets, including HotpotQA [30], 2WikiMultiHopQA [7], and Musique [26], increased the complexity by requiring agents to connect multiple pieces of evidence to derive an answer.”
Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies
Zhou, H., Wan, X., Sun, R., Palangi, H., Iqbal, S., Vulić, I., Korhonen, A., & Arık, S. Ö. (2025) · arXiv · doi:10.48550/arxiv.2502.02533
Tran, D., & Kiela, D. (2026) · arXiv · doi:10.48550/arxiv.2604.02460 · Cited by 47
“5-Flash, SAS-L is the strongest single-agent configuration in every MuSiQue panel, and its block averages remain above standard SAS throughout.”
InfluentialSynapse: Empowering LLM Agents with Episodic-Semantic Memory via Spreading Activation
Jiang, H., Chen, J., Pan, Y., Chen, L., You, W., Zhou, Y., Zhang, R., Abate, Y., & Liu, T. (2026) · Findings of the Association for Computational Linguistics: ACL 2026 · doi:10.18653/v1/2026.findings-acl.1108 · Cited by 2
A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents
Huang, W.-C., Zhang, W., Liang, Y., Bei, Y., Chen, Y., Feng, T., Pan, X., Tan, Z., Wang, Y., Wei, T., et al. (2026) · arXiv · doi:10.48550/arxiv.2602.06052 · Cited by 70
Mitigating Context Interference for Reliable and Efficient Search Agents
Xue, B., Wu, B., Qiao, S., Wang, S., Wang, R., Du, Y., Wang, H., Pan, J. Z., Yilmaz, E., Wong, K.-F., et al. (2026) · Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2026.acl-long.160
EvolKV: Evolutionary KV Cache Compression for LLM Inference
Yu, B., & Chai, Y. (2025) · Findings of the Association for Computational Linguistics: EMNLP 2025 · doi:10.18653/v1/2025.findings-emnlp.88
SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
Xia, P., Chen, J., Wang, H., Liu, J., Zeng, K., Wang, Y., Han, S., Zhou, Y., Zhao, X., Chen, H., et al. (2026) · arXiv · doi:10.48550/arxiv.2602.08234
Alkhaldi, T., Chu, C., & Kurohashi, S. (2023) · Lecture notes in networks and systems · doi:10.1007/978-3-031-38318-2_15 · Cited by 1
Multihop Question Answering, A Topological Approach for Graph Generation
Bahrami, R. A., & Yahyapour, R. (2024) · doi:10.1109/icnlp60986.2024.10692433
SimLayerKV: A Simple Framework for Layer-Level KV Cache ReductionPreprint
Zhang, X., Du, C., Du, C., Pang, T., Gao, W., & Lin, M. C. (2024) · Qeios · doi:10.32388/epai4t · Cited by 8
HR-SKGs: Hyper-Relational Semantic Knowledge Graphs for Multi-hop Reading Comprehension
Zhang, Y., Cheng, B. H., & Chen, Y.-L. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889591 · Cited by 1
Fact-Centric Knowledge Web for Information Retrieval
Sinha, R., & Shiramatsu, S. (2024) · IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) · doi:10.1109/wi-iat62293.2024.00067 · Cited by 1
DR − CoT: A Multi-Agent Framework for Enhanced Reasoning in Large Language Models
Ali, H., Ghosh, P., & Sharma, A. (2025) · International Conference on Recent Advances in Information Technology · doi:10.1109/rait65068.2025.11088893
MDBench: A Synthetic Multi-Document Reasoning Benchmark Generated with Knowledge Guidance
Peper, J. J., Qiu, W., Payani, A., & Wang, L. (2025) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2025.findings-acl.1312 · Cited by 3
Automated Question-Answer Generation for Evaluating Vietnamese RAG-Based Approaches
Nguyen, D.-H., & Nguyen, L. H. B. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-98164-7_21
Singh, A., Srivastav, J., Banerjee, J., Jindal, S., & Mohapatra, A. K. (2025) · International Conference on Networks and Cryptology (NETCRYPT) · doi:10.1109/netcrypt65877.2025.11102417
Corm: Cache Optimization with Recent Message for Large Language Model InferencePreprint
Huang, Z., Jiang, H., & Dai, J. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5388897
Step-Wise Selection from Multiple Reasoning Chains to Enhance LLMs for Multi-hop QA
Xu, T., Murayama, Y., & Izumi, K. (2025) · Transactions of the Japanese Society for Artificial Intelligence · doi:10.1527/tjsai.40-5_a-p21
Zhang, Y., Cheng, B. H., & Chen, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04549-2_11
Wang, Y., Wang, H., Wang, K., & Du, X. (2025) · International Conference on Computer Information Science and Application Technology (CISAT) · doi:10.1109/cisat66811.2025.11181923
Metadata
- Authors
- Trivedi, H., Balasubramanian, N., Khot, T., & Sabharwal, A.
- Affiliations
- Stony Brook University (US)
- Allen Institute for Artificial Intelligence (US)
- Corresponding author
- Trivedi, Harsh
- Balasubramanian, Niranjan
- Khot, Tushar
- Sabharwal, Ashish
- Venue
- Transactions of the Association for Computational Linguistics
- Publisher
- MIT Press
- Published
- 2022
- Volume
- 10
- Pages
- 539-554
- ISSN
- 2307-387X (ISSN-L)
- OpenAlex
- W3190126809
- Cited by
- 283
- References
- 53
- Citations by year
- 2026: 156 · 2025: 75 · 2024: 21 · 2023: 28 · 2022: 3
- FWCI
- 10.45
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- Transactions of the Association for Computational Linguistics (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1815358)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- shortcut learning, unanswerable questions
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.