Shuguo Hu | Searcharxiv

arXiv2026

AcupunctureBench: A Multimodal Benchmark for Evaluating Generative Models in the Acupuncture Domain

As large language models (LLMs) are increasingly applied in the field of traditional Chinese medicine (TCM), standardized benchmark evaluations for TCM have gradually emerged. Acupuncture is a crucial component of TCM. However, existing evaluation benchmarks are lacking in this domain. To address this gap, this paper proposes AcupunctureBench, the first independently constructed large-scale multimodal benchmark for the acupuncture domain, covering text, image, and video modalities. The AcupunctureBench spans multidimen sional knowledge in acupuncture, including acupuncture theory, meridians and acupoints, clinical reasoning, TCM syndromes, and practical acupoint operation. To achieve large-scale construction while ensuring medical professionalism, this work designs a human-machine collaborative data construction pipeline and proposes efficient deduplication strategies to reduce redundant samples, while extensively adopting data synthesis to mitigate data leak age risks. AcupunctureBench contains a total of 58,526 question samples and 1,216 video samples, covering multiple task types including objective questions, subjective question answering, case analysis, image understanding, image reasoning, and video understanding. Based on this benchmark, this paper evaluates 14 large language models, 14 large multimodal models, and 4 video foundation models, and further releases the first dedicated evaluation website for the acupuncture domain.

q-bio.QM↗

arXiv2025

Synergizing LLMs with Global Label Propagation for Multimodal Fake News Detection

Large Language Models (LLMs) can assist multimodal fake news detection by predicting pseudo labels. However, LLM-generated pseudo labels alone demonstrate poor performance compared to traditional detection methods, making their effective integration non-trivial. In this paper, we propose Global Label Propagation Network with LLM-based Pseudo Labeling (GLPN-LLM) for multimodal fake news detection, which integrates LLM capabilities via label propagation techniques. The global label propagation can utilize LLM-generated pseudo labels, enhancing prediction accuracy by propagating label information among all samples. For label propagation, a mask-based mechanism is designed to prevent label leakage during training by ensuring that training nodes do not propagate their own labels back to themselves. Experimental results on benchmark datasets show that by synergizing LLMs with label propagation, our model achieves superior performance over state-of-the-art baselines.

cs.CL↗