Publications (7)
Towards Faithful Sentimental Image Captioning via Evidence-Aware Multi-Agent Reasoning
Tiecheng Cai, Zexian Yang, Chao Chen +2
The paper introduces SEA-Cap, a multi‑agent system that extracts object‑level affective evidence from images and uses a generator, hallucination checker, and arbitrator to produce…
Constrained Paraphrase Consistency for LLM Hallucination Detection
Shanshan Lin, Dongsheng Hong, Sibo Ju +3
Large language models (LLMs) can generate factually inconsistent claims, motivating accurate and scalable hallucination detectors. Prior work largely enlarges training sets via syn…
Cross Paraphrastic Invariance Learning for Hallucination Detection
Shanshan Lin, Dongsheng Hong, Sibo Ju +3
Large language models (LLMs) frequently generate hallucinations, which are unsupported by a source document. To avoid costly LLM-as-evaluator pipelines and the heavy annotation dem…
BAED: a New Paradigm for Few-shot Graph Learning with Explanation in the Loop
Chao Chen, Xujia Li, Dongsheng Hong +4
The challenges of training and inference in few-shot environments persist in the area of graph representation learning. The quality and quantity of labels are often insufficient du…
ICME 2026 Grand Challenge on Cross-Scenario Defect Detection and Fine-Grained Severity Grading for High-Precision Manufacturing
Wei Sun, Weixia Zhang, Linhan Cao +30
This paper presents the IEEE International Conference on Multimedia and Expo (ICME) 2026 Grand Challenge on Cross-Scenario Defect Detection and Fine-Grained Severity Grading for Hi…
Explanation-Guided Adversarial Training for Robust and Interpretable Models
Chao Chen, Yanhui Chen, Shanshan Lin +4
Deep neural networks (DNNs) have achieved remarkable performance in many tasks, yet they often behave as opaque black boxes. Explanation-guided learning (EGL) methods steer DNNs us…
From Attribution to Action: Jointly ALIGNing Predictions and Explanations
Dongsheng Hong, Chao Chen, Yanhui Chen +3
Explanation-guided learning (EGL) has shown promise in aligning model predictions with interpretable reasoning, particularly in computer vision tasks. However, most approaches rely…