Yan Li

Dr. Yan Li


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 November 2023 in Expert Systems with Applications
Verified
Journal Article
Closed access
JWJinghua Wu
Jinghua Wu
TZTing Zhang
Ting Zhang
YLYan Li
Yan Li
GZGuangjuan Zhou
Guangjuan Zhou

18 March 2021 in Journal of Ambient Intelligence and Humanized Computing
Verified
Journal Article
Closed access
PDF file
JWJinghua Wu
Jinghua Wu
FZFujuan Zhang
Fujuan Zhang
JHJiali Han
Jiali Han
YLYan Li
Yan Li
YSYi Sun
Yi Sun

11 May 2024 in Expert Systems with Applications
Verified
Journal Article
Closed access
JWJinghua Wu
Jinghua Wu
WWWenzhe Wang
Wenzhe Wang
YLYan Li
Yan Li

18 March 2025 in Engineering Applications of Artificial Intelligence
Verified
Journal Article
Closed access
JWJinghua Wu
Jinghua Wu
YZYa Zhang
Ya Zhang
RCRuiyang Cao
Ruiyang Cao
YLYan Li
Yan Li

23 June 2026 in Information Processing & Management
Verified
Journal Article
Closed access
WXWenbo Xing
Wenbo Xing
YLYan Li
Yan Li
ZZZhiming Zhao
Zhiming Zhao

30 June 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
YLYan Li
Yan Li
YLYunqian Li
Yunqian Li
LZLong Zhang
Long Zhang
Generative AI has enabled industrial-scale production of high-fidelity fake reviews that evade traditional detectors. Existing multimodal methods rely on deterministic alignment assumptions, overlooking the stochastic variability of authentic expressions and the systematic cross-modal inconsistencies inherent in AI-generated content. This study proposes the Inconsistency-Driven Adaptive Modulation Network (IDAMN), shifting detection from surface plausibility to probabilistic structural consistency verification. IDAMN employs a Mixture Density Network to model the conditional distribution of authentic multimodal data across three inconsistency dimensions—text-image semantic, text-image affective, and text-rating—quantifying deviation as probabilistic surprisal rather than deterministic distance. An inconsistency-guided FiLM mechanism dynamically modulates features by amplifying informative dissonance signals while suppressing noise without fixed thresholds. On a 1,387-sample multimodal dataset, IDAMN achieves 95.32% accuracy and 95.31% F1 score, substantially outperforming ablation variants (removing MDN drops F1 to 0.7888) and large multimodal models including Qwen-3-VL-Plus (F1=0.6512) and GLM-4.6V-106B (F1=0.6667). These findings demonstrate that explicit probabilistic inconsistency modeling provides a robust, interpretable foundation for detecting AI-generated deception, with direct implications for platform governance and trustworthy decision support in AIGC-era digital markets.