{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T15:19:42Z","timestamp":1774711182316,"version":"3.50.1"},"reference-count":78,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T00:00:00Z","timestamp":1736899200000},"content-version":"vor","delay-in-days":14,"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\/501100010814","name":"Anhui Provincial Department of Education","doi-asserted-by":"publisher","award":["2022AH050319"],"award-info":[{"award-number":["2022AH050319"]}],"id":[{"id":"10.13039\/501100010814","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                    Fake news detection (FND) is a critical task in natural language processing (NLP) focused on identifying and mitigating the spread of misinformation. Large language models (LLMs) have recently shown remarkable abilities in understanding semantics and performing logical inference. However, their tendency to generate hallucinations poses significant challenges in accurately detecting deceptive content, leading to suboptimal performance. In addition, existing FND methods often underutilize the extensive prior knowledge embedded within LLMs, resulting in less effective classification outcomes. To address these issues, we propose the CAPE\u2013FND framework, context\u2010aware prompt engineering, designed for enhancing FND tasks. This framework employs unique veracity\u2010oriented context\u2010aware constraints, background information, and analogical reasoning to mitigate LLM hallucinations and utilizes self\u2010adaptive bootstrap prompting optimization to improve LLM predictions. It further refines initial LLM prompts through adaptive iterative optimization using a random search bootstrap algorithm, maximizing the efficacy of LLM prompting. Extensive zero\u2010shot and few\u2010shot experiments using GPT\u20103.5\u2010turbo across multiple public datasets demonstrate the effectiveness and robustness of our CAPE\u2013FND framework, even surpassing advanced GPT\u20104.0 and human performance in certain scenarios. To support further LLM\u2013based FND, we have made our approach\u2019s code publicly available on GitHub (our CAPE\u2013FND code:\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/albert-jin\/CAPE-FND\">https:\/\/github.com\/albert-jin\/CAPE-FND<\/jats:ext-link>\n                    [Accessed on 2024.09]).\n                  <\/jats:p>","DOI":"10.1155\/int\/5920142","type":"journal-article","created":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T10:39:54Z","timestamp":1736937594000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["Veracity\u2010Oriented Context\u2010Aware Large Language Models\u2013Based Prompting Optimization for Fake News Detection"],"prefix":"10.1155","volume":"2025","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6656-6061","authenticated-orcid":false,"given":"Weiqiang","family":"Jin","sequence":"first","affiliation":[]},{"given":"Yang","family":"Gao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5630-2070","authenticated-orcid":false,"given":"Tao","family":"Tao","sequence":"additional","affiliation":[]},{"given":"Xiujun","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Ningwei","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Baohai","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Biao","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2025,1,15]]},"reference":[{"key":"e_1_2_16_1_2","doi-asserted-by":"crossref","unstructured":"ZhaoX. OuyangS. YuZ. WuM. andLiL. Pre-trained Language Models Can Be Fully Zero-Shot Learners Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) 2023 Toronto Canada Association for Computational Linguistics 15590\u201315606.","DOI":"10.18653\/v1\/2023.acl-long.869"},{"key":"e_1_2_16_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3137597.3137600"},{"key":"e_1_2_16_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2022.09.001"},{"key":"e_1_2_16_4_2","unstructured":"OpenAI GPT-4 Technical Report 2023 https:\/\/arxiv.org\/abs\/2303.08774."},{"key":"e_1_2_16_5_2","doi-asserted-by":"crossref","unstructured":"MaoR. ChenG. ZhangX. GuerinF. andCambriaE. CalzolariN. KanM. Y. HosteV. LenciA. SaktiS. andXueN. GPTEval: A Survey on Assessments of ChatGPT and GPT-4 Proceedings of the 2024 Joint International Conference on Computational Linguistics Language Resources and Evaluation (LREC-COLING 2024)ELRA and ICCL 2024 May 2024 Torino Italia 7844\u20137866.","DOI":"10.63317\/3dhqzf3tvt2z"},{"key":"e_1_2_16_6_2","unstructured":"TouvronH. LavrilT. IzacardG.et al. LLaMA: Open and Efficient Foundation Language Models 2023."},{"key":"e_1_2_16_7_2","article-title":"The Claude 3 Model Family: Opus, Sonnet, Haiku","author":"Ai A.","year":"2023","journal-title":"Anthropic AI LAB"},{"key":"e_1_2_16_8_2","volume-title":"NIPS \u201922. NIPS","author":"Wei J.","year":"2024"},{"key":"e_1_2_16_9_2","volume-title":"Large Language Models Are Zero-Shot Reasoners","author":"Kojima T.","year":"2022"},{"key":"e_1_2_16_10_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.64"},{"key":"e_1_2_16_11_2","volume-title":"NIPS \u201920. NIPS","author":"Brown T. B.","year":"2020"},{"key":"e_1_2_16_12_2","volume-title":"ICLR","author":"Yao S.","year":"2023"},{"key":"e_1_2_16_13_2","volume-title":"Training Verifiers to Solve Math Word Problems","author":"Cobbe K.","year":"2021"},{"key":"e_1_2_16_14_2","unstructured":"HanglooS.andAroraB. Fake News Detection Tools and Methods \u2013 A Review 2021 https:\/\/arxiv.org\/pdf\/2112.11185."},{"key":"e_1_2_16_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106991"},{"key":"e_1_2_16_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.scs.2020.102652"},{"key":"e_1_2_16_17_2","volume-title":"MVAE: Multimodal Variational Autoencoder for Fake News Detection","author":"Khattar D.","year":"2019"},{"key":"e_1_2_16_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-47436-2_27"},{"key":"e_1_2_16_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2617078"},{"key":"e_1_2_16_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132877"},{"key":"e_1_2_16_21_2","doi-asserted-by":"publisher","DOI":"10.1017\/nlp.2024.38"},{"key":"e_1_2_16_22_2","article-title":"Indonesian News Stance Classification Based on Hybrid Bidirectional LSTM and Transformer-Based Embedding","author":"Setiawan E.","year":"2024","journal-title":"Journal of Intelligent Systems"},{"key":"e_1_2_16_23_2","first-page":"34","volume-title":"CSW \u201922","author":"Ameli L.","year":"2023"},{"key":"e_1_2_16_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3395046"},{"key":"e_1_2_16_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3323503.3360648"},{"key":"e_1_2_16_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3305260"},{"key":"e_1_2_16_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615015"},{"key":"e_1_2_16_28_2","doi-asserted-by":"crossref","unstructured":"HuS. DingN. WangH.et al. Knowledgeable Prompt-Tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) 2022 Dublin Ireland Association for Computational Linguistics 2225\u20132240.","DOI":"10.18653\/v1\/2022.acl-long.158"},{"key":"e_1_2_16_29_2","unstructured":"LiuY. OttM. GoyalN.et al. RoBERTa: A Robustly Optimized BERT Pretraining Approach 2019 https:\/\/arxiv.org\/abs\/1907.11692."},{"key":"e_1_2_16_30_2","doi-asserted-by":"crossref","unstructured":"SchickT.andSch\u00fctzeH. Exploiting Cloze-Questions for Few-Shot Text Classification and Natural Language Inference Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume 2021 Association for Computational Linguistics 255\u2013269.","DOI":"10.18653\/v1\/2021.eacl-main.20"},{"key":"e_1_2_16_31_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.720"},{"key":"e_1_2_16_32_2","doi-asserted-by":"crossref","unstructured":"WangW. Y. Liar Liar Pants on Fire: A New Benchmark Dataset for Fake News Detection Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) ACL 2017 Vancouver Canada Association for Computational Linguistics 422\u2013426.","DOI":"10.18653\/v1\/P17-2067"},{"key":"e_1_2_16_33_2","volume-title":"FakeNewsNet: A Data Repository With News Content, Social Context and Spatialtemporal Information for Studying Fake News on Social Media","author":"Shu K.","year":"2019"},{"key":"e_1_2_16_34_2","volume-title":"CREDBANK: A Large-Scale Social Media Corpus with Associated Credibility Annotations","author":"Mitra T.","year":"2015"},{"key":"e_1_2_16_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/sp.2012.34"},{"key":"e_1_2_16_36_2","doi-asserted-by":"crossref","unstructured":"PotthastM. KieselJ. ReinartzK. BevendorffJ. andSteinB. A Stylometric Inquiry into Hyperpartisan and Fake News Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) 2018 Melbourne Australia Association for Computational Linguistics 231\u2013240.","DOI":"10.18653\/v1\/P18-1022"},{"key":"e_1_2_16_37_2","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v11i1.14976"},{"key":"e_1_2_16_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3377478"},{"key":"e_1_2_16_39_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.11.022"},{"key":"e_1_2_16_40_2","doi-asserted-by":"publisher","DOI":"10.3390\/computation9020020"},{"key":"e_1_2_16_41_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.03.036"},{"key":"e_1_2_16_42_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10588-018-09280-3"},{"key":"e_1_2_16_43_2","unstructured":"P\u00e9rez-RosasV. KleinbergB. LefevreA. andMihalceaR. Automatic Detection of Fake News Proceedings of the 27th International Conference on Computational Linguistics 2018 Association for Computational Linguistics Santa Fe NM 3391\u20133401."},{"key":"e_1_2_16_44_2","doi-asserted-by":"crossref","unstructured":"KarimiH.andTangJ. Learning Hierarchical Discourse-Level Structure for Fake News Detection 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) 2019 Association for Computational Linguistics Minneapolis Minnesota 3432\u20133442.","DOI":"10.18653\/v1\/N19-1347"},{"key":"e_1_2_16_45_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11268"},{"key":"e_1_2_16_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/mipr.2018.00092"},{"key":"e_1_2_16_47_2","volume-title":"Beyond News Contents: The Role of Social Context for Fake News Detection","author":"Shu K.","year":"2018"},{"key":"e_1_2_16_48_2","volume-title":"Studying Fake News via Network Analysis: Detection and Mitigation","author":"Shu K.","year":"2019"},{"key":"e_1_2_16_49_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2020.07.017"},{"key":"e_1_2_16_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/icde.2015.7113322"},{"key":"e_1_2_16_51_2","doi-asserted-by":"crossref","unstructured":"VaibhavV. MandyamR. andHovyE. Do Sentence Interactions Matter? Leveraging Sentence Level Representations for Fake News Classification Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13) 2019 Hong Kong Association for Computational Linguistics 134\u2013139.","DOI":"10.18653\/v1\/D19-5316"},{"key":"e_1_2_16_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330935"},{"key":"e_1_2_16_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412046"},{"key":"e_1_2_16_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123454"},{"key":"e_1_2_16_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350850"},{"key":"e_1_2_16_56_2","doi-asserted-by":"crossref","unstructured":"PopatK. MukherjeeS. YatesA. andWeikumG. DeClarE: Debunking Fake News and False Claims Using Evidence-Aware Deep Learning Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing 2018 Brussels Belgium Association for Computational Linguistics 22\u201332.","DOI":"10.18653\/v1\/D18-1003"},{"key":"e_1_2_16_57_2","volume-title":"FakeDetector: Effective Fake News Detection with Deep Diffusive Neural Network","author":"Zhang J.","year":"2020"},{"key":"e_1_2_16_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3341161.3342894"},{"key":"e_1_2_16_59_2","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","author":"Devlin J.","year":"2019"},{"key":"e_1_2_16_60_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-10183-2"},{"key":"e_1_2_16_61_2","volume-title":"Detecting Deception: A Comprehensive Review of Machine Learning Approaches to Fake News Detection","author":"Zaheer O.","year":"2024"},{"key":"e_1_2_16_62_2","volume-title":"Defending against Neural Fake News","author":"Zellers R.","year":"2019"},{"key":"e_1_2_16_63_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-70039-9"},{"key":"e_1_2_16_64_2","volume-title":"A Comparative Study of Offline Models and Online LLMs in Fake News Detection","author":"Xu R.","year":"2024"},{"key":"e_1_2_16_65_2","volume-title":"LLM-GAN: Construct Generative Adversarial Network through Large Language Models for Explainable Fake News Detection","author":"Wang Y.","year":"2024"},{"key":"e_1_2_16_66_2","volume-title":"DAAD: Dynamic Analysis and Adaptive Discriminator for Fake News Detection","author":"Su X.","year":"2024"},{"key":"e_1_2_16_67_2","doi-asserted-by":"crossref","unstructured":"MinS. LyuX. HoltzmanA.et al. Rethinking the Role of Demonstrations: What Makes In-Context Learning Work? Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing EMNLP 2022 Abu Dhabi UAE Association for Computational Linguistics 11048\u201311064.","DOI":"10.18653\/v1\/2022.emnlp-main.759"},{"key":"e_1_2_16_68_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.ijcnlp-main.20"},{"key":"e_1_2_16_69_2","volume-title":"Gemini: A Family of Highly Capable Multimodal Models","author":"Team G.","year":"2024"},{"key":"e_1_2_16_70_2","unstructured":"GlmT. ZengA. XuB.et al. ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools 2024."},{"key":"e_1_2_16_71_2","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"e_1_2_16_72_2","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-024-02274-5"},{"key":"e_1_2_16_73_2","volume-title":"NIPS \u201920","author":"Lewis P.","year":"2020"},{"key":"e_1_2_16_74_2","unstructured":"ZhaoT. WallaceE. FengS. KleinD. andSinghS. Calibrate before Use: Improving Few-Shot Performance of Language Models 2021 12697\u201312706."},{"key":"e_1_2_16_75_2","unstructured":"SanhV. WebsonA. RaffelC.et al. Multitask Prompted Training Enables Zero-Shot Task Generalization 2022."},{"key":"e_1_2_16_76_2","unstructured":"ZhuangL. WayneL. YaS. andJunZ. A Robustly Optimized BERT Pre-training Approach with Post-training Proceedings of the 20th Chinese National Conference on Computational Linguistics 2021 Huhhot China Chinese Information Processing Society of China 1218\u20131227."},{"key":"e_1_2_16_77_2","doi-asserted-by":"publisher","DOI":"10.1007\/s13278-023-01104-w"},{"key":"e_1_2_16_78_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110235"}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/5920142","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1155\/int\/5920142","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/5920142","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T18:11:28Z","timestamp":1772993488000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/int\/5920142"}},"subtitle":[],"editor":[{"given":"Eugenio","family":"Vocaturo","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":78,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1155\/int\/5920142"],"URL":"https:\/\/doi.org\/10.1155\/int\/5920142","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":"2024-09-19","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-12-28","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-01-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"5920142"}}