Beamaggr: Beam aggregation reasoning over multi-source knowledge for multi-hop question answering
Open accessAbstract
Zheng Chu, Jingchang Chen, Qianglong Chen, Haotian Wang, Kun Zhu, Xiyuan Du, Weijiang Yu, Ming Liu, Bing Qin. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
Question decomposition breaks down complex multi-hop questions into simpler sub-questions, reducing difficulty of reasoning and planning, and enabling more accurate retrieval.
“It breaks down the complex multi-hop question into simpler sub-questions, thereby reducing the difficulty of reasoning and planning, and enabling more accurate retrieval.”
From Self-Critique Guided Iterative Reasoning for Multi-hop Question Answering (2025) · cites this paper as Chu et al., 2024a
Section 3.1 describes decomposing complex multi-hop questions into simpler sub-questions and solving them bottom-up. Section 5.1 says sub-questions provide clearer queries and that decomposition leads to more accurate retrieval. The paper does not establish the separate claim that decomposition reduces the difficulty of reasoning and planning. (LLM, conf=0.85)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
The publisher hasn’t deposited this paper’s reference list.
Research works printed but not linked: 7
- PMLR.
- Shulin Cao, Jiajie Zhang, Jiaxin Shi, Xin Lv, Zijun Yao, Qi Tian, Lei Hou, and Juanzi Li. 2023. Probabilistic tree-of-thought reasoning for answering knowledge- intensive complex questions. In Findings of the As- sociation for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023, pages 12541- 12560. Association for Computational Linguistics.
- Xingxuan Li, Ruochen Zhao, Yew Ken Chia, Bosheng Ding, Shafiq Joty, Soujanya Poria, and Lidong Bing. 2024. Chain-of-knowledge: Grounding large lan- guage models via dynamic knowledge adapting over heterogeneous sources. In The Twelfth International Conference on Learning Representations.
- Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le, Ed H. Chi, Sharan Narang, Aakanksha Chowd- hery, and Denny Zhou. 2023. Self-consistency improves chain of thought reasoning in language models. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net.
- Wenhao Yu, Dan Iter, Shuohang Wang, Yichong Xu, Mingxuan Ju, Soumya Sanyal, Chenguang Zhu, Michael Zeng, and Meng Jiang. 2023. Generate rather than retrieve: Large language models are strong context generators. In The Eleventh Inter- national Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. Open- Review.net.
- Zhuosheng Zhang, Aston Zhang, Mu Li, and Alex Smola. 2023c. Automatic chain of thought prompt- ing in large language models. In The Eleventh In- ternational Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. Open- Review.net.
- Denny Zhou, Nathanael Schärli, Le Hou, Jason Wei, Nathan Scales, Xuezhi Wang, Dale Schuurmans, Claire Cui, Olivier Bousquet, Quoc V. Le, and Ed H. Chi. 2023. Least-to-most prompting enables com- plex reasoning in large language models. In The Eleventh International Conference on Learning Rep- resentations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net. Question: Who is the performer of Live at this studio that employs the person who coined the term theatre of the absurd? Decompose: "Who is the performer of Live at this studio that employs the person who coined the term theatre of the absurd?": ["Where did the person who coined the term the theatre of the absurd work?", "Who is the performer at the Live at the #1 event?"], "Where did the person who coined the term the theatre of the absurd work?": ["Who coined the term the theatre of the absurd", "Where is #1 worked?"] Question: Who is the general treasurer of the state where Israel Arnold House is located? Decompose: "Who is the general treasurer of the state where Israel Arnold House is located?": ["What state is Israel Arnold House located?", "Who is the general treasurer of #1?"] Question: What weekly publication in the place of death of George Townsend is issued by the employer of the Yale labor historian who advised younger historians? Decompose: "What weekly publication in the place of death of George Townsend is issued by the employer of the Yale labor historian who advised younger historians?": ["Where the Yale labor historian who advised younger labor historians works?", "Where did George Townsend die?", "What weekly publication in #2 is issued by #1?"], "Where the Yale labor historian who advised younger labor historians works?": ["Which Yale labor historian advised other younger labor historians?", "Where #1 works?"] Question: When was the SEC championship game between the winner of the most national titles in NCAA football and Georgia? Decompose: "When was the SEC championship game between the winner of the most national titles in NCAA football and Georgia?": ["Who has the most national titles in NCAA football?", "When was the SEC championship game between #1 and georgia?"] Question: Who sings Never Say Never with the performer of As Long as You Love Me? Decompose: "Who sings Never Say Never with the performer of As Long as You Love Me?": ["Who is the per- former of As Long as You Love Me?", "Who sings Never Say Never with #1?"] ...... Demonstrations of Question Decomposition Figure 10: Demonstrations of question decomposition. (24 shot) Question: When did the director of film Hypocrite (Film) die? Answer: The film Hypocrite was directed by Miguel Morayta. Miguel Morayta died on 19 June 2013. So the answer is **19 June 2013**.
Cited by
Sorted by citations
Huang, L., Yu, W., Ma, W., Zhong, W., Feng, Z., Wang, H., Chen, Q., Peng, W., Feng, X., Qin, B., et al. (2025) · ACM Transactions on Information Systems · doi:10.1145/3703155 · Cited by 2,142 · see citing works
Self-citationHallucination Mitigation for Retrieval-Augmented Large Language Models: A Review
Zhang, W., & Zhang, J. (2025) · Mathematics · doi:10.3390/math13050856 · Cited by 145 · see citing works
Adaptive Orchestration of Modular Generative Information Access Systems
Hoveyda, M., Oosterhuis, H., de Vries, A. D., de Rijke, M., & Hasibi, F. (2025) · Annual International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3726302.3730351 · Cited by 11 · see citing works
Li, 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 2 · see citing works
Atomic Fact Decomposition Helps Attributed Question Answering
Yan, Z., Wang, J., Chen, J., Li, X., Liang, J., Li, R., & Pan, J. Z. (2025) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2025.3608716 · Cited by 6 · see citing works
Self-citationSelf-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
Self-citationLiu, M., Yang, C., Jiang, B., & Lei, C. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209576
Self-citationRetrieval-Augmented Generation for Multi-Hop Question Answering Based on Structured Planning
Huang, Y., Yang, L., Yang, X.-H., & Xu, X. (2026) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3789506
- Authors
- Chu, Z., Chen, J., Chen, Q., Wang, H., Zhu, K., Du, X., Yu, W., Liu, M., & Qin, B.
- Affiliations
- Harbin Institute of Technology (CN)
- Sun Yat-sen University (CN)
- Venue
- Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2024
- Pages
- 1229-1248
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W4402685455
- Cited by
- 11
- References
- 0
- Citations by year
- 2026: 3 · 2025: 7 · 2024: 1
- FWCI
- 2.65
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (U22B2059)
- 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 › Information Systems › Information Retrieval and Search Behavior
- Keywords
- multi-hop question answering, knowledge aggregation, beam search, question answering
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
