{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:05:30Z","timestamp":1775228730730,"version":"3.50.1"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T00:00:00Z","timestamp":1769644800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T00:00:00Z","timestamp":1775174400000},"content-version":"vor","delay-in-days":64,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62466016"],"award-info":[{"award-number":["62466016"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J. King Saud Univ. Comput. Inf. Sci."],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Multi-hop question answering (MHQA) requires models to perform reasoning across multiple text segments to answer complex questions. However, existing methods often overlook temporal dependencies between facts during reasoning path construction, resulting in illogical inference chains and reduced reasoning accuracy. This study enhances the modeling of time-sensitive information in MHQA to optimize the construction of reasoning paths, thereby improving the inference accuracy and robustness of QA systems in real-world scientific scenarios. The objective is to achieve a dynamic balance between reasoning precision and computational efficiency. A Time-Aware Graph Attention Mechanism is first introduced to dynamically construct entity-relation graphs within documents, incorporating timestamp features to capture event sequences and temporal dependencies. Then, a Dual-Level Temporal Path Selector is proposed to identify optimal reasoning paths at both the sentence and entity levels, ensuring temporal consistency and semantic completeness throughout the reasoning process. Experiments are conducted on two benchmark MHQA datasets, HotpotQA and MuSiQue-full, evaluating the model\u2019s accuracy, path coherence, and temporal consistency. Results show that the proposed model achieves a Joint Exact Match score of 74.3% on HotpotQA, outperforming the current best-performing model Pathformer (71.5%) by 2.8%. On MuSiQue-full, the model attains an Answer F1 score of 87.1%, exceeding DecompT5\u2019s 85.2%, and reaches a temporal consistency score of 91.3. These findings confirm the effectiveness of the proposed time-aware path construction strategy in enhancing MHQA performance. The proposed time-enhanced reasoning approach significantly improves logical coherence, temporal reasoning, and adaptive efficiency across varying reasoning depths, demonstrating an effective balance between performance gains and manageable computational costs. This study provides valuable insights for developing temporally-aware QA systems applicable to real-world scenarios such as historical analysis and legal reasoning.<\/jats:p>","DOI":"10.1007\/s44443-026-00471-6","type":"journal-article","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T14:53:57Z","timestamp":1769698437000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimizing multi-hop question answering reasoning through time-aware path construction"],"prefix":"10.1007","volume":"38","author":[{"given":"Xue","family":"Yang","sequence":"first","affiliation":[]},{"given":"Siling","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Shan","family":"Xue","sequence":"additional","affiliation":[]},{"given":"Qingkui","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Mengxing","family":"Huang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,29]]},"reference":[{"key":"471_CR1","doi-asserted-by":"crossref","unstructured":"Biswas B, Ramnath R (2024) \u201cEfficient and interpretable information retrieval for product question answering with heterogeneous data.\u201d arXiv:2405.13173","DOI":"10.63317\/39iywyys266p"},{"key":"471_CR2","doi-asserted-by":"crossref","unstructured":"Chakraborty N, Lukovnikov D, Maheshwari G, Trivedi P, Lehmann J, Fischer A (2021) \u201cIntroduction to neural network-based question answering over knowledge graphs.\u201d Wiley Interdiscip. Rev Data Min Knowl Discov 11(3):e1389","DOI":"10.1002\/widm.1389"},{"issue":"3","key":"471_CR3","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1017\/S1351324921000292","volume":"29","author":"C Chen","year":"2023","unstructured":"Chen C, Bunescu R, Marling C (2023) A semantic parsing pipeline for context-dependent question answering over temporally structured data. Nat Lang Eng 29(3):769\u2013793","journal-title":"Nat Lang Eng"},{"key":"471_CR4","doi-asserted-by":"publisher","first-page":"14438","DOI":"10.18653\/v1\/2024.findings-emnlp.844","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2024, Miami","author":"RR Chen","year":"2024","unstructured":"Chen RR, Jiang WF, Qin CW et al (2024) LLM-Based Multi-Hop Question Answering with Knowledge Graph Integration in Evolving Environments. In: Florida USA (ed) Findings of the Association for Computational Linguistics: EMNLP 2024, Miami. Association for Computational Linguistics, pp 14438\u201314451"},{"issue":"5","key":"471_CR5","doi-asserted-by":"publisher","first-page":"376","DOI":"10.3390\/aerospace12050376","volume":"12","author":"S Chen","year":"2025","unstructured":"Chen S, Pan W, Wang Y, Chen S, Wang X (2025) Research on the method of air traffic control instruction keyword extraction based on the Roberta-Attention-BiLSTM-CRF model. Aerospace 12(5):376","journal-title":"Aerospace"},{"key":"471_CR6","doi-asserted-by":"crossref","unstructured":"Cheng K, Lin G, Fei H, Yu L, Ali MA, Hu L, Wang D (2024) \u201cMulti-hop question answering under temporal knowledge editing.\u201d arXiv:2404.00492","DOI":"10.18653\/v1\/2025.findings-acl.130"},{"key":"471_CR7","doi-asserted-by":"crossref","unstructured":"Fang Y, Sun S, Gan Z, Pillai R, Wang S, Liu J (2020) \u201cHierarchical graph network for multi-hop question answering.\u201d in Proc. Conf. Empir. Methods Nat. Lang. Process. (EMNLP), pp. 8823\u20138838","DOI":"10.18653\/v1\/2020.emnlp-main.710"},{"key":"471_CR8","unstructured":"Fazili B, Goswami K, Modani N, Nair I (2024) \u201cGenSco: Can question decomposition based passage alignment improve question answering?.\u201d arXiv:2407.10245"},{"key":"471_CR9","unstructured":"Giammei L (2025) \u201cAn integrated approach to causality: the role of causal graphs.\u201d arXiv:2503.19878 [cs.CL]"},{"issue":"1","key":"471_CR10","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1075\/elt.00024.hai","volume":"3","author":"H Haider","year":"2021","unstructured":"Haider H (2021) Grammar change: A case of Darwinian cognitive evolution. Evol Linguist Theory 3(1):6\u201355","journal-title":"Evol Linguist Theory"},{"key":"471_CR11","unstructured":"He Y, Gorinski PJ, Staliunaite I, Stenetorp P (2023) \u201cGraph attention with hierarchies for multi-hop question answering.\u201d arXiv:2301.11792"},{"issue":"21","key":"471_CR12","doi-asserted-by":"publisher","first-page":"11811","DOI":"10.3390\/ijms252111811","volume":"25","author":"TV Ivanisenko","year":"2024","unstructured":"Ivanisenko TV, Demenkov PS, Ivanisenko VA (2024) An accurate and efficient approach to knowledge extraction from scientific publications using structured ontology models, graph neural networks, and large language models. Int J Mol Sci 25(21):11811","journal-title":"Int J Mol Sci"},{"key":"471_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.datak.2024.102300","volume":"151","author":"W Jia","year":"2024","unstructured":"Jia W, Ma R, Yan L, Niu W, Ma Z (2024) Time-aware structure matching for temporal knowledge graph alignment. Data Knowl Eng 151:102300","journal-title":"Data Knowl Eng"},{"key":"471_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.conbuildmat.2021.126162","volume":"321","author":"N Kheradmandi","year":"2022","unstructured":"Kheradmandi N, Mehranfar V (2022) A critical review and comparative study on image segmentation-based techniques for pavement crack detection. Constr Build Mater 321:126162","journal-title":"Constr Build Mater"},{"key":"471_CR15","doi-asserted-by":"publisher","first-page":"105613","DOI":"10.1109\/ACCESS.2024.3435343","volume":"15","author":"BB K\u00f6me\u00e7oglu","year":"2024","unstructured":"K\u00f6me\u00e7oglu BB, Yilmaz B (2024) Event graph-based news clustering: The role of named entity-centered subgraphs. IEEE Access 15:105613\u2013105632","journal-title":"IEEE Access"},{"issue":"1","key":"471_CR16","doi-asserted-by":"publisher","first-page":"40","DOI":"10.3758\/s13423-020-01792-x","volume":"28","author":"AA Kumar","year":"2021","unstructured":"Kumar AA (2021) Semantic memory: A review of methods, models, and current challenges. Psychon Bull Rev 28(1):40\u201380","journal-title":"Psychon Bull Rev"},{"key":"471_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12911-021-01622-7","volume":"21","author":"Y Lan","year":"2021","unstructured":"Lan Y, He S, Liu K, Zeng X, Liu S, Zhao J (2021) Path-based knowledge reasoning with textual semantic information for medical knowledge graph completion. BMC Med Inform Decis Mak 21:1\u201312","journal-title":"BMC Med Inform Decis Mak"},{"issue":"1","key":"471_CR18","doi-asserted-by":"publisher","first-page":"653","DOI":"10.32604\/cmc.2023.046424","volume":"78","author":"H Li","year":"2024","unstructured":"Li H, Yu Y, Zhao Z, Tang X (2024) A time series short-term prediction method based on multi-granularity event matching and alignment. Comput Mater Continua 78(1):653","journal-title":"Comput Mater Continua"},{"issue":"5","key":"471_CR19","doi-asserted-by":"publisher","first-page":"1837","DOI":"10.1007\/s11280-021-00911-5","volume":"24","author":"J Liao","year":"2021","unstructured":"Liao J, Zhao X, Tang J, Zeng W, Tan Z (2021) To hop or not, that is the question: Towards effective multi-hop reasoning over knowledge graphs. World Wide Web 24(5):1837\u20131856","journal-title":"World Wide Web"},{"key":"471_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103300","volume":"213","author":"M Luo","year":"2021","unstructured":"Luo M, Chang X, Gong C (2021) Reliable shot identification for complex event detection via visual-semantic embedding. Comput Vis Image Underst 213:103300","journal-title":"Comput Vis Image Underst"},{"key":"471_CR21","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.1066","volume":"8","author":"M Maisonnave","year":"2022","unstructured":"Maisonnave M, Delbianco F, Tohme F, Milios E, Maguitman AG (2022) Causal graph extraction from news: A comparative study of time-series causality learning techniques. PeerJ Comput Sci 8:e1066","journal-title":"PeerJ Comput Sci"},{"issue":"5","key":"471_CR22","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1561\/1500000102","volume":"17","author":"V Mavi","year":"2024","unstructured":"Mavi V, Jangra A, Jatowt A (2024) Multi-hop question answering. Found Trends Inf Retr 17(5):457\u2013586","journal-title":"Found Trends Inf Retr"},{"key":"471_CR23","doi-asserted-by":"crossref","unstructured":"Meng C, Arabzadeh N, Askari A, Aliannejadi M, de Rijke M (2024) \u201cQuery performance prediction using relevance judgments generated by large language models.\u201d ACM Trans. Inf. Syst., pp. 1\u201334","DOI":"10.1145\/3736402"},{"issue":"7","key":"471_CR24","doi-asserted-by":"publisher","first-page":"3580","DOI":"10.1109\/TKDE.2024.3352100","volume":"36","author":"S Pan","year":"2024","unstructured":"Pan S, Luo L, Wang Y et al (2024) Unifying large language models and knowledge graphs: A roadmap. IEEE Trans Knowl Data Eng 36(7):3580\u20133599","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"471_CR25","doi-asserted-by":"crossref","unstructured":"Qian X, Zhang Y, Zhao Y, Zhou B, Sui X, Zhang L, Song K (2024) \u201cTimeR4: time-aware retrieval-augmented large language models for temporal knowledge graph question answering,\u201d in Proc. Conf. Empir. Methods Nat. Lang. Process. (EMNLP), pp. 6942\u20136952","DOI":"10.18653\/v1\/2024.emnlp-main.394"},{"issue":"2","key":"471_CR26","first-page":"135","volume":"26","author":"RK Raut","year":"2024","unstructured":"Raut RK, Kumar S (2024) An integrated approach of TAM and TPB with financial literacy and perceived risk for influence on online trading intention. Digit Policy Regul Gov 26(2):135\u2013152","journal-title":"Digit Policy Regul Gov"},{"issue":"9","key":"471_CR27","doi-asserted-by":"publisher","first-page":"318","DOI":"10.3390\/fi16090318","volume":"16","author":"AG Vrahatis","year":"2024","unstructured":"Vrahatis AG, Lazaros K, Kotsiantis S (2024) Graph attention networks: A comprehensive review of methods and applications. Future Internet 16(9):318","journal-title":"Future Internet"},{"key":"471_CR28","doi-asserted-by":"crossref","unstructured":"Wei J, Li Z, Zhang C, Ma H (2025) Fusing grid and adaptive region features for image captioning. Image Vis Comput 157:105513","DOI":"10.1016\/j.imavis.2025.105513"},{"key":"471_CR29","doi-asserted-by":"crossref","unstructured":"Wu D, Wang Z, Zhao W (2024) XLNet-CNN-GRU dual-channel aspect-level review text sentiment classification method. Multimed Tools Appl 83(2):5871\u20135892","DOI":"10.1007\/s11042-023-15026-4"},{"issue":"1","key":"471_CR30","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1109\/COMST.2022.3223224","volume":"25","author":"W Yang","year":"2022","unstructured":"Yang W, Du H, Liew ZQ, Lim WYB, Xiong Z, Niyato D, Chi X, Shen X, Miao C (2022) Semantic communications for future internet: Fundamentals, applications, and challenges. IEEE Commun Surv Tutor 25(1):213\u2013250","journal-title":"IEEE Commun Surv Tutor"},{"issue":"1","key":"471_CR31","first-page":"725","volume":"35","author":"J Yu","year":"2021","unstructured":"Yu J, Su Q, Quan X, Yin J (2021) Multi-hop reasoning question generation and its application. IEEE Trans Knowl Data Eng 35(1):725\u2013740","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"471_CR32","unstructured":"Yu X, Guo B, Luo S, Wang J, Ji T, Wu Y (2024) \u201cAntlm: Bridging causal and masked language models,\u201d arXiv preprint arXiv:2412.03275"},{"issue":"2","key":"471_CR33","first-page":"1","volume":"41","author":"Y Zhao","year":"2022","unstructured":"Zhao Y, Wang X, Chen J, Wang Y, Tang W, He X, Xie H (2022) Time-aware path reasoning on knowledge graph for recommendation. ACM Trans Inf Syst 41(2):1\u201326","journal-title":"ACM Trans Inf Syst"},{"issue":"7","key":"471_CR34","doi-asserted-by":"publisher","first-page":"3416","DOI":"10.3390\/app12073416","volume":"12","author":"W Zheng","year":"2022","unstructured":"Zheng W, Zhou Y, Liu S, Tian J, Yang B, Yin L (2022) A deep fusion matching network semantic reasoning model. Appl Sci 12(7):3416","journal-title":"Appl Sci"},{"issue":"9","key":"471_CR35","doi-asserted-by":"publisher","first-page":"9115","DOI":"10.1007\/s10462-023-10400-y","volume":"56","author":"X Zhong","year":"2023","unstructured":"Zhong X, Cambria E (2023) Time expression recognition and normalization: A survey. Artif Intell Rev 56(9):9115\u20139140","journal-title":"Artif Intell Rev"}],"container-title":["Journal of King Saud University Computer and Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44443-026-00471-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-026-00471-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-026-00471-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T14:18:57Z","timestamp":1775225937000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44443-026-00471-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,29]]},"references-count":35,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["471"],"URL":"https:\/\/doi.org\/10.1007\/s44443-026-00471-6","relation":{},"ISSN":["1319-1578","2213-1248"],"issn-type":[{"value":"1319-1578","type":"print"},{"value":"2213-1248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,29]]},"assertion":[{"value":"18 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"107"}}