{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T03:31:50Z","timestamp":1775187110865,"version":"3.50.1"},"reference-count":38,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T00:00:00Z","timestamp":1764115200000},"content-version":"vor","delay-in-days":329,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100017611","name":"Social Science Foundation of Shaanxi Province","doi-asserted-by":"publisher","award":["2024K015"],"award-info":[{"award-number":["2024K015"]}],"id":[{"id":"10.13039\/501100017611","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:p>\n                    This paper introduces a cost\u2010effective prompt optimization strategy for ancient Chinese word segmentation using large language models, aiming to mitigate the substantial computational resources and training expenses of fine\u2010tuning. We developed two knowledge\u2010enhanced frameworks, a General Knowledge Prompt framework and a Domain\u2010Specific Knowledge Prompt framework, and evaluated their effectiveness across various ancient Chinese corpora using seven mainstream LLMs, including ERNIE Bot, Qwen, SparkDesk, DeepSeek, ChatGPT, Gemini, and Copilot. Our findings confirm that both prompt frameworks enhance the segmentation capability of LLMs to varying extents, with the Domain\u2010Specific Knowledge Prompt framework yielding the most significant improvements. Notably, the DeepSeek model achieves 94.01%\n                    <jats:italic>F<\/jats:italic>\n                    1 score (94.24% precision, 93.79% recall) on the test set, while the Qwen model demonstrates a remarkable 15.73% increase in the\n                    <jats:italic>F<\/jats:italic>\n                    1 score with the Domain\u2010Specific Knowledge Prompt framework. Our ablation studies indicate that the entries Rules and Examples are the most crucial to the success of prompt frameworks, effectively addressing the challenges of rule inconsistency and insufficient annotated data.\n                  <\/jats:p>","DOI":"10.1155\/int\/9612240","type":"journal-article","created":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T12:57:51Z","timestamp":1764161871000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Improving Ancient Chinese Word Segmentation With Knowledge\u2010Enhanced Prompting for Large Language Models"],"prefix":"10.1155","volume":"2025","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0267-110X","authenticated-orcid":false,"given":"Meng-Tian","family":"Tang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6903-8774","authenticated-orcid":false,"given":"Cheng-Gang","family":"Mi","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2025,11,26]]},"reference":[{"key":"e_1_2_12_1_2","first-page":"336","article-title":"A Statistical Method for Finding Word Boundaries in Chinese Text","volume":"4","author":"Sproat R.","year":"1990","journal-title":"Computer Processing of Chinese and Oriental Languages"},{"key":"e_1_2_12_2_2","unstructured":"KeY.-H. Construction of Ancient Chinese Word Segmentation and Part-of-Speech Corpus 1 Proceedings of the 23rd Chinese National Conference on Computational Linguistics 2024 819\u2013829 https:\/\/aclanthology.org\/2024.ccl-1.64\/."},{"key":"e_1_2_12_3_2","doi-asserted-by":"publisher","DOI":"10.3969\/j.issn.1002-1167.2022.06.006"},{"key":"e_1_2_12_4_2","doi-asserted-by":"publisher","DOI":"10.12154\/j.qbzlgz.2024.01.008"},{"key":"e_1_2_12_5_2","doi-asserted-by":"publisher","DOI":"10.3969\/j.issn.1003-0077.2008.04.005"},{"key":"e_1_2_12_6_2","doi-asserted-by":"publisher","DOI":"10.3969\/j.issn.1003-0077.2010.02.005"},{"key":"e_1_2_12_7_2","doi-asserted-by":"publisher","DOI":"10.13734\/j.cnki.1000-531520230316"},{"key":"e_1_2_12_8_2","first-page":"1","article-title":"Word Segmentation for Ancient Chinese Texts Based on Nonparametric Bayesian Models and Deep Learning","volume":"34","author":"Yu J.","year":"2020","journal-title":"Journal of Chinese Information Processing"},{"key":"e_1_2_12_9_2","doi-asserted-by":"publisher","DOI":"10.3969\/j.issn.1003-0077.2023.08.017"},{"key":"e_1_2_12_10_2","doi-asserted-by":"publisher","DOI":"10.3969\/j.issn.1003-0077.2012.02.003"},{"key":"e_1_2_12_11_2","doi-asserted-by":"crossref","unstructured":"ZhengX. ChenH. andXuT. Deep Learning for Chinese Word Segmentation and POStagging Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing 2013 647\u2013657 https:\/\/aclanthology.org\/D13-1061\/ https:\/\/doi.org\/10.18653\/v1\/d13-1061.","DOI":"10.18653\/v1\/D13-1061"},{"key":"e_1_2_12_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2881280"},{"key":"e_1_2_12_13_2","volume-title":"Research on Lexical Analysis of Ancient Texts Based on Deep Learning","author":"Li C.-M.","year":"2018"},{"key":"e_1_2_12_14_2","doi-asserted-by":"publisher","DOI":"10.3969\/j.issn.1007-1423.2020.16.012"},{"key":"e_1_2_12_15_2","doi-asserted-by":"crossref","unstructured":"HuoS.andChenW. Ancient Chinese Sentence Segmentation and Punctuation on Xunzi LLM Proceedings of the Third Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) @ LREC-COLING-2024 2024 https:\/\/aclanthology.org\/2024.lt4hala-1.29\/.","DOI":"10.63317\/3uyrexiueebm"},{"key":"e_1_2_12_16_2","first-page":"1","article-title":"Research on Cross-Lingual Automatic Word Segmentation for Ancient Texts Based on Large Language Models","author":"Wang X.","year":"2024","journal-title":"Library Journal"},{"key":"e_1_2_12_17_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.07619"},{"key":"e_1_2_12_18_2","doi-asserted-by":"crossref","unstructured":"LuY. BartoloM. MooreA. RiedelS. andStenetorpP. Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity 1 Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics 2022 8086\u20138098 https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.556.","DOI":"10.18653\/v1\/2022.acl-long.556"},{"key":"e_1_2_12_19_2","unstructured":"Dair.Ai Prompt Engineering Guide 2024 https:\/\/www.promptingguide.ai\/zh\/introduction."},{"key":"e_1_2_12_20_2","doi-asserted-by":"publisher","DOI":"10.15888\/j.cnki.csa.009782"},{"key":"e_1_2_12_21_2","doi-asserted-by":"publisher","DOI":"10.14188\/j.1671-8836.2024.0027"},{"key":"e_1_2_12_22_2","unstructured":"ZhangJ. WibertM. ZhouH.et al. A Study of Biomedical Relation Extraction Using GPT Models Proceedings of AMIA Joint Summits on Translational Science 2024 391\u2013400."},{"key":"e_1_2_12_23_2","first-page":"1","article-title":"Entity Relation Extraction of Chinese Medical Text Based on Large Language Model and Prompt Engineering","author":"Duan Y.","year":"2024","journal-title":"Data Analysis and Knowledge Discovery"},{"key":"e_1_2_12_24_2","doi-asserted-by":"publisher","DOI":"10.16353\/j.cnki.1000-7490.2025.04.017"},{"key":"e_1_2_12_25_2","doi-asserted-by":"crossref","unstructured":"ShenZ. LangH. WangB. KimY. andSontagD. Learning to Decode Collaboratively with Multiple Language Models Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics 2024 12974\u201312990 https:\/\/doi.org\/10.18653\/v1\/2024.acl-long.701.","DOI":"10.18653\/v1\/2024.acl-long.701"},{"key":"e_1_2_12_26_2","doi-asserted-by":"publisher","DOI":"10.19820\/j.cnki.ISSN2096-7411.2024.04.002"},{"key":"e_1_2_12_27_2","unstructured":"VatsalS.andHarshD. A Survey of Prompt Engineering Methods in Large Language Models for Different NLP Tasks 2024 https:\/\/arxiv.org\/abs\/2407.12994."},{"key":"e_1_2_12_28_2","unstructured":"BrownT. B. MannB. RyderN.et al. Language Models Are Few-Shot Learners Prozceedings of the 34th International Conference on Neural Information Processing Systems 2020 https:\/\/doi.org\/10.48550\/arXiv.2005.14165."},{"key":"e_1_2_12_29_2","volume-title":"Stylistic Classification","author":"Qian C.","year":"1992"},{"key":"e_1_2_12_30_2","volume-title":"Studies on the Genres, Styles, and Forms of Classical Chinese Literature","author":"Wu C.","year":"2024"},{"key":"e_1_2_12_31_2","volume-title":"A History of Vernacular Literature","author":"Hu S.","year":"1999"},{"key":"e_1_2_12_32_2","volume-title":"A History of Chinese Word Classes","author":"Zhou S.","year":"2018"},{"key":"e_1_2_12_33_2","first-page":"402","article-title":"On Studies of Loanwords in Modern Chinese","volume":"20","author":"Wang R.","year":"2021","journal-title":"Linguistic Sciences"},{"key":"e_1_2_12_34_2","volume-title":"Chinese Loanwords","author":"Shi Y.","year":"2000"},{"key":"e_1_2_12_35_2","volume-title":"A Study on Loanwords of the Chinese Dictionary","author":"Li Y.","year":"2023"},{"key":"e_1_2_12_36_2","doi-asserted-by":"publisher","DOI":"10.16512\/j.cnki.jsjjy.2017.12.005"},{"key":"e_1_2_12_37_2","doi-asserted-by":"publisher","DOI":"10.16499\/j.cnki.1003-5397.2023.04.005"},{"key":"e_1_2_12_38_2","volume-title":"Chinese Literature: A Very Short Introduction","author":"Knight S.","year":"2021"}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/9612240","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1155\/int\/9612240","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/9612240","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T18:05:01Z","timestamp":1772993101000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/int\/9612240"}},"subtitle":[],"editor":[{"given":"Richard","family":"Murray","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1155\/int\/9612240"],"URL":"https:\/\/doi.org\/10.1155\/int\/9612240","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"value":"0884-8173","type":"print"},{"value":"1098-111X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2025-05-24","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-16","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"9612240"}}