A prompting multi-task learning-based veracity dissemination consistency reasoning augmentation for few-shot fake news detection. Jin, W., Wang, N., Tao, T., Jiang, M., Xing, Y., Zhao, B., Wu, H., Duan, H., & Yang, G. Engineering Applications of Artificial Intelligence, 144(May 2024):110122, Elsevier Ltd, 2025.
A prompting multi-task learning-based veracity dissemination consistency reasoning augmentation for few-shot fake news detection [link]Website  doi  abstract   bibtex   
With the rise of social media, traditional news channels are being supplanted, leading to increased prevalence of fake news. Existing Fake News Detection (FEND) methods, while effective in fully-supervised settings, struggle with data scarcity and lack robustness in few-shot scenarios. Social pattern analysis shows that users tend to share information aligning with their existing beliefs, a behavior known as ”Confirmation Bias”. This bias influences how news spreads within social groups, where consistent sharing patterns among closely connected users often serve as credible indicators of news authenticity. We refer to this phenomenon as the ”user spreading news engagement bias”. Inspired by this, we propose a novel Prompting Multi-Task Learning framework guided by news veracity Dissemination Consistency reasoning augmentation for few-shot FEND, abbreviated as PMTL-DisCo, which leverages advanced Artificial Intelligence (AI) techniques, such as multi-task learning (MTL), prompt-based tuning, and masked language model (MLM), for feature extraction and optimization. Unlike prior works that primarily rely on pre-trained language models (PLMs) for feature extraction, PMTL-DisCo integrates the following innovations: (1) an auxiliary task, ”news distributed representation optimization,” that leverages dissemination consistency signals from neighboring news cases to enhance feature learning. (2) a high-quality, expanded label words-based verbalizer engineering, which improves prompt-tuning performance through adaptive multi-label mappings. (3) a multi-neighbor reasoning enhancement strategy, which refines predictions by incorporating the veracity features of socially connected news cases. These innovations address the limitations of existing FEND methods, particularly their inability to exploit cross-news dissemination patterns effectively. Extensive experiments and ablation studies on three widely used benchmarks demonstrate that PMTL-DisCo outperforms state-of-the-art few-shot FEND models, showcasing its superior generalization and robustness in low-resource settings.
@article{
 title = {A prompting multi-task learning-based veracity dissemination consistency reasoning augmentation for few-shot fake news detection},
 type = {article},
 year = {2025},
 keywords = {Dissemination consistency reasoning augmentation,Few-shot fake news detection,Masked language model,Multi-task learning,Prompt-based tuning,User spreading news engagement bias},
 pages = {110122},
 volume = {144},
 websites = {https://doi.org/10.1016/j.engappai.2025.110122},
 publisher = {Elsevier Ltd},
 id = {63a3ac25-0a12-31eb-a7ba-df8971bb0375},
 created = {2025-05-30T17:24:30.249Z},
 file_attached = {false},
 profile_id = {d5b9f595-4104-33d2-b640-e84dee1b7ded},
 last_modified = {2025-05-30T17:24:30.249Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 private_publication = {false},
 abstract = {With the rise of social media, traditional news channels are being supplanted, leading to increased prevalence of fake news. Existing Fake News Detection (FEND) methods, while effective in fully-supervised settings, struggle with data scarcity and lack robustness in few-shot scenarios. Social pattern analysis shows that users tend to share information aligning with their existing beliefs, a behavior known as ”Confirmation Bias”. This bias influences how news spreads within social groups, where consistent sharing patterns among closely connected users often serve as credible indicators of news authenticity. We refer to this phenomenon as the ”user spreading news engagement bias”. Inspired by this, we propose a novel Prompting Multi-Task Learning framework guided by news veracity Dissemination Consistency reasoning augmentation for few-shot FEND, abbreviated as PMTL-DisCo, which leverages advanced Artificial Intelligence (AI) techniques, such as multi-task learning (MTL), prompt-based tuning, and masked language model (MLM), for feature extraction and optimization. Unlike prior works that primarily rely on pre-trained language models (PLMs) for feature extraction, PMTL-DisCo integrates the following innovations: (1) an auxiliary task, ”news distributed representation optimization,” that leverages dissemination consistency signals from neighboring news cases to enhance feature learning. (2) a high-quality, expanded label words-based verbalizer engineering, which improves prompt-tuning performance through adaptive multi-label mappings. (3) a multi-neighbor reasoning enhancement strategy, which refines predictions by incorporating the veracity features of socially connected news cases. These innovations address the limitations of existing FEND methods, particularly their inability to exploit cross-news dissemination patterns effectively. Extensive experiments and ablation studies on three widely used benchmarks demonstrate that PMTL-DisCo outperforms state-of-the-art few-shot FEND models, showcasing its superior generalization and robustness in low-resource settings.},
 bibtype = {article},
 author = {Jin, Weiqiang and Wang, Ningwei and Tao, Tao and Jiang, Mengying and Xing, Yebei and Zhao, Biao and Wu, Hao and Duan, Haibin and Yang, Guang},
 doi = {10.1016/j.engappai.2025.110122},
 journal = {Engineering Applications of Artificial Intelligence},
 number = {May 2024}
}
Downloads: 0
About
Documentation
Keywords
Search
Users
Terms and Conditions of Use
Privacy Policy
Sitemap
© BibBase.org 2021