{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T21:49:32Z","timestamp":1769809772458,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":42,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819556397","type":"print"},{"value":"9789819556403","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-5640-3_32","type":"book-chapter","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T21:08:14Z","timestamp":1769720894000},"page":"496-511","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Prior Knowledge Augmentation for Reinforcement Learning-Based Knowledge Graph Reasoning"],"prefix":"10.1007","author":[{"given":"Yiyang","family":"Weng","sequence":"first","affiliation":[]},{"given":"Tong","family":"Li","sequence":"additional","affiliation":[]},{"given":"Zifang","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Junrui","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Zhen","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,30]]},"reference":[{"key":"32_CR1","unstructured":"Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. NeurIPS 26 (2013)"},{"key":"32_CR2","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. NeurIPS 33, 1877\u20131901 (2020)","journal-title":"NeurIPS"},{"issue":"6","key":"32_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3643806","volume":"56","author":"J Cao","year":"2024","unstructured":"Cao, J., Fang, J., Meng, Z., Liang, S.: Knowledge graph embedding: a survey from the perspective of representation spaces. ACM Comput. Surv. 56(6), 1\u201342 (2024)","journal-title":"ACM Comput. Surv."},{"key":"32_CR4","unstructured":"Das, R., et al.: Go for a walk and arrive at the answer: reasoning over paths in knowledge bases using reinforcement learning. arXiv preprint arXiv:1711.05851 (2017)"},{"key":"32_CR5","doi-asserted-by":"crossref","unstructured":"Dettmers, T., Minervini, P., Stenetorp, P., Riedel, S.: Convolutional 2d knowledge graph embeddings. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11573"},{"key":"32_CR6","unstructured":"Dong, Q., et al.: A survey on in-context learning. arXiv preprint arXiv:2301.00234 (2022)"},{"key":"32_CR7","doi-asserted-by":"crossref","unstructured":"Gal\u00e1rraga, L.A., Teflioudi, C., Hose, K., Suchanek, F.: Amie: association rule mining under incomplete evidence in ontological knowledge bases. In: Proceedings of the 22nd International Conference on World Wide Web, pp. 413\u2013422 (2013)","DOI":"10.1145\/2488388.2488425"},{"key":"32_CR8","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: AISTATS, pp. 249\u2013256. JMLR Workshop and Conference Proceedings (2010)"},{"issue":"8","key":"32_CR9","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"32_CR10","doi-asserted-by":"crossref","unstructured":"Hou, Z., Jin, X., Li, Z., Bai, L.: Rule-aware reinforcement learning for knowledge graph reasoning. In: ACL-IJCNLP 2021, pp. 4687\u20134692 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.412"},{"key":"32_CR11","doi-asserted-by":"crossref","unstructured":"Jiang, C., et al.: Path spuriousness- aware reinforcement learning for multi-hop knowledge graph reasoning. In: EACL, pp. 3181\u20133192 (2023)","DOI":"10.18653\/v1\/2023.eacl-main.232"},{"key":"32_CR12","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"32_CR13","first-page":"22199","volume":"35","author":"T Kojima","year":"2022","unstructured":"Kojima, T., Gu, S.S., Reid, M., Matsuo, Y., Iwasawa, Y.: Large language models are zero-shot reasoners. NeurIPS 35, 22199\u201322213 (2022)","journal-title":"NeurIPS"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"Lin, X.V., Socher, R., Xiong, C.: Multi-hop knowledge graph reasoning with reward shaping. In: EMNLP, pp. 3243\u20133253 (2018)","DOI":"10.18653\/v1\/D18-1362"},{"issue":"9","key":"32_CR15","first-page":"1","volume":"55","author":"P Liu","year":"2023","unstructured":"Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., Neubig, G.: Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing. ACM Comput. Surv. 55(9), 1\u201335 (2023)","journal-title":"ACM Comput. Surv."},{"key":"32_CR16","doi-asserted-by":"crossref","unstructured":"Lu, Y., Bartolo, M., Moore, A., Riedel, S., Stenetorp, P.: Fantastically ordered prompts and where to find them: overcoming few-shot prompt order sensitivity. arXiv preprint arXiv:2104.08786 (2021)","DOI":"10.18653\/v1\/2022.acl-long.556"},{"key":"32_CR17","doi-asserted-by":"crossref","unstructured":"Lv, X., et al.: Is multi-hop reasoning really explainable? Towards benchmarking reasoning interpretability. In: EMNLP, pp. 8899\u20138911 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.700"},{"issue":"7","key":"32_CR18","first-page":"3580","volume":"36","author":"S Pan","year":"2024","unstructured":"Pan, S., Luo, L., Wang, Y., Chen, C., Wang, J., Wu, X.: Unifying large language models and knowledge graphs: a roadmap. TKDE 36(7), 3580\u20133599 (2024)","journal-title":"TKDE"},{"key":"32_CR19","doi-asserted-by":"crossref","unstructured":"Puterman, M.L.: Markov decision processes: discrete stochastic dynamic programming (1994)","DOI":"10.1002\/9780470316887"},{"issue":"8","key":"32_CR20","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)","journal-title":"OpenAI blog"},{"key":"32_CR21","doi-asserted-by":"crossref","unstructured":"Safavi, T., Koutra, D.: Codex: a comprehensive knowledge graph completion benchmark. In: EMNLP, pp. 8328\u20138350 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.669"},{"key":"32_CR22","unstructured":"Sahoo, P., Singh, A.K., Saha, S., Jain, V., Mondal, S., Chadha, A.: A systematic survey of prompt engineering in large language models: techniques and applications. arXiv preprint arXiv:2402.07927 (2024)"},{"key":"32_CR23","unstructured":"Sun, J., et al.: Think- on-graph: deep and responsible reasoning of large language model with knowledge graph. arXiv preprint arXiv:2307.07697 (2023)"},{"key":"32_CR24","unstructured":"Touvron, H., et al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"issue":"10","key":"32_CR25","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1145\/2629489","volume":"57","author":"D Vrande\u010di\u0107","year":"2014","unstructured":"Vrande\u010di\u0107, D., Kr\u00f6tzsch, M.: Wikidata: a free collaborative knowledgebase. Commun. ACM 57(10), 78\u201385 (2014)","journal-title":"Commun. ACM"},{"key":"32_CR26","unstructured":"Wei, J., et al.: Finetuned language models are zero-shot learners. arXiv preprint arXiv:2109.01652 (2021)"},{"key":"32_CR27","first-page":"24824","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. NeurIPS 35, 24824\u201324837 (2022)","journal-title":"NeurIPS"},{"key":"32_CR28","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1023\/A:1022672621406","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8, 229\u2013256 (1992)","journal-title":"Mach. Learn."},{"key":"32_CR29","doi-asserted-by":"crossref","unstructured":"Xiong, W., Hoang, T., Wang, W.Y.: Deeppath: a reinforcement learning method for knowledge graph reasoning. arXiv preprint arXiv:1707.06690 (2017)","DOI":"10.18653\/v1\/D17-1060"},{"key":"32_CR30","unstructured":"Yang, B., Yih, W.T., He, X., Gao, J., Deng, L.: Embedding entities and relations for learning and inference in knowledge bases. arXiv preprint arXiv:1412.6575 (2014)"},{"key":"32_CR31","doi-asserted-by":"crossref","unstructured":"Zhou, X., Wang, P., Luo, Q., Pan, Z.: Multi-hop knowledge graph reasoning based on hyperbolic knowledge graph embedding and reinforcement learning. In: Proceedings of the 10th International Joint Conference on Knowledge Graphs, pp. 1\u20139 (2021)","DOI":"10.1145\/3502223.3502224"},{"key":"32_CR32","doi-asserted-by":"crossref","unstructured":"Meilicke, C., Chekol, M.W., Fink, M., Stuckenschmidt, H.: Reinforced anytime bottom up rule learning for knowledge graph completion. arXiv preprint arXiv:2004.04412 (2020)","DOI":"10.24963\/ijcai.2019\/435"},{"issue":"5","key":"32_CR33","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1007\/s11280-024-01297-w","volume":"27","author":"Y Zhu","year":"2024","unstructured":"Zhu, Y., et al.: Llms for knowledge graph construction and reasoning: recent capabilities and future opportunities. World Wide Web 27(5), 58 (2024)","journal-title":"World Wide Web"},{"key":"32_CR34","unstructured":"Trouillon, T., Welbl, J., Riedel, S., Gaussier, \u00c9., Bouchard, G.: Complex embeddings for simple link prediction. In: ICML, pp. 2071\u20132080. PMLR (2016)"},{"key":"32_CR35","unstructured":"Zhang, S., Tay, Y., Yao, L., Liu, Q.: Quaternion knowledge graph embeddings. NeurIPS 32 (2019)"},{"key":"32_CR36","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.112948","volume":"141","author":"X Chen","year":"2020","unstructured":"Chen, X., Jia, S., Xiang, Y.: A review: knowledge reasoning over knowledge graph. Expert Syst. Appl. 141, 112948 (2020)","journal-title":"Expert Syst. Appl."},{"key":"32_CR37","unstructured":"Bianchi, F., Rossiello, G., Costabello, L., Palmonari, M., Minervini, P.: Knowledge graph embeddings and explainable AI. In: Knowledge Graphs for Explainable Artificial Intelligence: Foundations, Applications and Challenges, pp. 49\u201372. IOS Press (2020)"},{"key":"32_CR38","unstructured":"Guo, J., Du, L., Liu, H., Zhou, M., He, X., Han, S.: Gpt4graph: can large language models understand graph structured data? An empirical evaluation and benchmarking. arXiv preprint arXiv:2305.15066 (2023)"},{"key":"32_CR39","doi-asserted-by":"crossref","unstructured":"Sewak, M., Sewak, M.: Policy-based reinforcement learning approaches: Stochastic policy gradient and the reinforce algorithm. In: Deep Reinforcement Learning: Frontiers of Artificial Intelligence, pp. 127\u2013140 (2019)","DOI":"10.1007\/978-981-13-8285-7_10"},{"key":"32_CR40","doi-asserted-by":"crossref","unstructured":"Toutanova, K., Chen, D.: Observed versus latent features for knowledge base and text inference. In: Proceedings of the 3rd Workshop on Continuous Vector Space Models and their Compositionality, pp. 57\u201366 (2015)","DOI":"10.18653\/v1\/W15-4007"},{"key":"32_CR41","doi-asserted-by":"publisher","unstructured":"Li, H., Wei, J., Yu, J., Jiang, Y.: Enhancing embedding and hierarchical reward shaping for multi-hop reasoning with reinforcement learning. In: Sheng, Q.Z., et al. (eds.) Advanced Data Mining and Applications. ADMA 2024. LNCS, vol. 15388, pp. 414\u2013429. Springer, Singapore (2025). https:\/\/doi.org\/10.1007\/978-981-96-0814-0_27","DOI":"10.1007\/978-981-96-0814-0_27"},{"issue":"6","key":"32_CR42","doi-asserted-by":"publisher","first-page":"1101","DOI":"10.26599\/TST.2022.9010063","volume":"28","author":"H Zhang","year":"2023","unstructured":"Zhang, H., Lu, G., Qin, K., Du, K.: Ainvr: adaptive learning rewards for knowledge graph reasoning using agent trajectories. Tsinghua Sci. Technol. 28(6), 1101\u20131114 (2023)","journal-title":"Tsinghua Sci. Technol."}],"container-title":["Lecture Notes in Computer Science","Web and Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5640-3_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T21:08:21Z","timestamp":1769720901000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5640-3_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819556397","9789819556403"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5640-3_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"30 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"APWeb-WAIM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International Conference on Web and Big Data","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenyang","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"apwebwaim2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/apweb2025.sau.edu.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}