Haoxuan Zhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Haoxuan Zhu has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Beining Wu
Hangzhou Dianzi University
1 shared publication - Chuncong Wang
Zhejiang Jinhui Digital Technology Co., Ltd., Yaojiang Development Center, No. 305 Huancheng North Road, Hangzhou 310006, China
1 shared publication - Feiwei Qin
Hangzhou Dianzi University
1 shared publication - Fuyou Mao
School of Electronic Information, Central South University, Changsha 410083, China
1 shared publication - Han Xue
School of Humanities, Arts and Digital Media, Hangzhou Dianzi University, Hangzhou 310018, China
1 shared publication - Hengyue Hu
School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou 310018, China
1 shared publication
Latest Publications
- Open Access
- 22 September 2026
- Published by MDPI AG in Electronics
- Vol. 15 (19) , 4355
TRACE-FND: A Constrained Evidence-Agent Workflow with Trainable Graph Adjudication for Multimodal Fake-News Detection
Multimodal misinformation often preserves individually plausible text and images while manipulating their relation, provenance, timing, or omitted context. Existing detectors mainly learn fused correlations or verify normalized claims, leaving temporal validity, source reliability, evidence conflict, and material omission weakly modeled. We introduce TRACE-FND, a constrained evidence-agent workflow with trainable graph adjudication for post-level multimodal fake news detection. Frozen structured agents convert each raw post into typed observations, truth/deception/omission hypotheses, and hypothesis-conditioned retrieval queries. Admissible candidates are normalized into immutable evidence cards; a trainable stance head and relation-aware graph discriminator then produce hypothesis-conditioned representations, while an evidence contract admits only card-cited arguments. A single calibrated judge maps the base, graph, hypothesis, debate, evidence-quality, and uncertainty features to the final label and confidence. The paper explicitly defines the frozen/trainable boundary, supervision, and one-to-one correspondence between mathematical objects and executable modules. Across Fakeddit-MM, Weibo-2017, and Multi-Fake-DetectiVE, the Teacher improves Macro-F1 over the strongest external baseline by 1.65, 1.48, and 1.60 points, respectively; paired tests support the first two gains, whereas the smaller Multi-Fake-DetectiVE test is not statistically conclusive. TRACE-FND also improves evidence quality, omission awareness, and temporal robustness, while a distilled Student reduces cached inference cost.
- 22 September 2026
- Published by MDPI AG in Electronics
- Vol. 15 (19) , 4355
Open AccessTRACE-FND: A Constrained Evidence-Agent Workflow with Trainable Graph Adjudication for Multimodal Fake-News Detection
Multimodal misinformation often preserves individually plausible text and images while manipulating their relation, provenance, timing, or omitted context. Existing detectors mainly learn fused correlations or verify normalized claims, leaving temporal validity, source reliability, evidence conflict, and material omission weakly modeled. We introduce TRACE-FND, a constrained evidence-agent workflow with trainable graph adjudication for post-level multimodal fake news detection. Frozen structured agents convert each raw post into typed observations, truth/deception/omission hypotheses, and hypothesis-conditioned retrieval queries. Admissible candidates are normalized into immutable evidence cards; a trainable stance head and relation-aware graph discriminator then produce hypothesis-conditioned representations, while an evidence contract admits only card-cited arguments. A single calibrated judge maps the base, graph, hypothesis, debate, evidence-quality, and uncertainty features to the final label and confidence. The paper explicitly defines the frozen/trainable boundary, supervision, and one-to-one correspondence between mathematical objects and executable modules. Across Fakeddit-MM, Weibo-2017, and Multi-Fake-DetectiVE, the Teacher improves Macro-F1 over the strongest external baseline by 1.65, 1.48, and 1.60 points, respectively; paired tests support the first two gains, whereas the smaller Multi-Fake-DetectiVE test is not statistically conclusive. TRACE-FND also improves evidence quality, omission awareness, and temporal robustness, while a distilled Student reduces cached inference cost.