Zhihong Zhu

Zhihong Zhu

Auto-generated profile, based on publicly available information

Zhihong Zhu

Peking University, Beijing, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
21 October 2024
Verified
Conference Paper
Open access
DXDerong Xu
Derong Xu
ZZZiheng Zhang
Ziheng Zhang
ZZZhihong Zhu
Zhihong Zhu
ZLZhenxi Lin
Zhenxi Lin
QLQidong Liu
Qidong Liu
YZYefeng Zheng
Yefeng Zheng
Model editing aims to precisely alter the behaviors of large language models (LLMs) in relation to specific knowledge, while leaving unrelated knowledge intact. This approach has proven effective in addressing issues of hallucination and outdated information in LLMs. However, the potential of using model editing to modify knowledge in the medical field remains largely unexplored, even though resolving hallucination is a pressing need in this area. Our observations indicate that current methods face significant challenges in dealing with specialized and complex knowledge in medical domain. Therefore, we propose MedLaSA, a novel Layer-wise Scalable Adapter strategy for medical model editing. MedLaSA harnesses the strengths of both adding extra parameters and locate-then-edit methods for medical model editing. We utilize causal tracing to identify the association of knowledge in neurons across different layers, and generate a corresponding scale set from the association value for each piece of knowledge. Subsequently, we incorporate scalable adapters into the dense layers of LLMs. These adapters are assigned scaling values based on the corresponding specific knowledge, which allows for the adjustment of the adapter's weight and rank. The more similar the content, the more consistent the scale between them. This ensures precise editing of semantically identical knowledge while avoiding impact on unrelated knowledge. To evaluate the editing impact on the behaviours of LLMs, we propose two model editing studies for medical domain: (1) editing factual knowledge for medical specialization and (2) editing the explanatory ability for complex knowledge. We build two novel medical benchmarking datasets and introduce a series of challenging and comprehensive metrics. Extensive experiments on medical LLMs demonstrate the editing efficiency of MedLaSA, without affecting unrelated knowledge.

30 June 2025
Verified
Conference Paper
Open access
YLYuqi Li
Yuqi Li
QLQingqing Long
Qingqing Long
YZYihang Zhou
Yihang Zhou
RZRan Zhang
Ran Zhang
ZNZhiyuan Ning
Zhiyuan Ning
Meng XiaoMeng Xiao
Meng Xiao

28 October 2024
Verified
Conference Paper
Open access
YXYifeng Xie
Yifeng Xie
ZZZhihong Zhu
Zhihong Zhu
XCXin Chen
Xin Chen
ZCZhanpeng Chen
Zhanpeng Chen
ZHZhiqi Huang
Zhiqi Huang
In the field of multi-modal learning, model parameters are typically large, necessitating the use of parameter-efficient fine-tuning (PEFT) techniques. These methods have been pivotal in enhancing training efficiency for downstream tasks in almost all situations. However, directly applying PEFT methods struggles to fully address the intricate demands of multi-modal tasks, such as multi-modal sarcasm detection (MSD), which demands the extraction and comparison of cues from different modalities. MSD, particularly when reliant on textual and visual modalities, faces challenges in identifying sarcasm's incongruity. This issue often arises from the lack of intermodality interaction during tuning, resulting in a disconnect between textual and visual information. In this paper, we introduce a novel approach called Bi-directional Adapter (BA), designated as MoBA. This approach is designed to minimize training parameters while enhancing the model's ability to interpret sarcasm across modalities. By facilitating an exchange between textual and visual information through a low-rank representation, our method adeptly captures the nuances of sarcastic expressions with a reduced number of training parameters. Our empirical studies, carried out on two publicly accessible and emerging datasets, demonstrate that our model substantially improves sarcasm detection accuracy. These findings indicate that our approach provides a more reliable and efficient solution to address the complexities of MSD.

28 October 2024
Verified
Conference Paper
Open access
ZZZhihong Zhu
Zhihong Zhu
XCXuxin Cheng
Xuxin Cheng
ZCZhaorun Chen
Zhaorun Chen
YCYuyan Chen
Yuyan Chen
YZYunyan Zhang
Yunyan Zhang
BXBowen Xing
Bowen Xing
Multi-modal intent detection (MID) aims to comprehend users' intentions through diverse modalities, which has received widespread attention in dialogue systems. Despite the promising advancements in complex fusion mechanisms or architecture designs, challenges remain due to: (1) various noise and redundancy in both visual and audio modalities and (2) long-tailed distributions of intent categories. In this paper, to tackle the above two issues, we propose InMu-Net, a simple yet effective framework for MID from the Information bottleneck and Multi-sensory processing perspective. Our contributions lie in three aspects. First, we devise a denoising bottleneck module to filter out the intent-irrelevant information in the fused feature; Second, we introduce a saliency preservation loss to prevent the dropping of intent-relevant information; Ultimately, kurtosis regulation is introduced to maintain representation smoothness during the filtering process, mitigating the adverse impact of the long tail distribution. Comprehensive experiments on two MID benchmark datasets demonstrate the effectiveness of InMu-Net and its vital components. Impressively, a series of analyses reveal our denoising potential and robustness in low-resource, modality corruption, cross-architecture and cross-task scenarios.

4 March 2024
Verified
Conference Paper
Open access
ZZZhihong Zhu
Zhihong Zhu
XCXuxin Cheng
Xuxin Cheng
HLHongxiang Li
Hongxiang Li
YLYaowei Li
Yaowei Li
YZYuexian Zou
Yuexian Zou
Multi-intent spoken language understanding (SLU) has garnered increasing attention since it can handle complex utterances expressing multiple intents in real-world scenarios. However, existing joint models are disturbed by label statistical frequencies, or adopt homogeneous graphs to capture interactions between the different types (e.g., intent and slot) of label nodes, thereby limiting the performance. To overcome these limitations, we propose Dual Heterogeneous Graph Label Interaction for multi-intent SLU, named DHLG. Concretely, we propose a global static heterogeneous label graph interaction layer to model both intra- and inter-label statistical dependencies across the entire training corpus. Based on this, we introduce a local dynamic heterogeneous label graph layer to further facilitate adaptive interactions between intents and slots for each utterance. Extensive experiments and analyses on two widely-used benchmark datasets demonstrate the superiority of our proposed DHLG over state-of-the-art methods.

27 February 2026 in IEEE Transactions on Big Data
Verified
Journal Article
Closed access
QLQingqing Long
Qingqing Long
SLShuai Liu
Shuai Liu
NCNing Cao
Ning Cao
ZRZhicheng Ren
Zhicheng Ren
XLXiao Luo
Xiao Luo
YZYuanchun Zhou
Yuanchun Zhou
Large Language Models (LLMs) have achieved prominent success in various applications, driven by their foundational capabilities and strong generalization potential. While their impact on natural language processing is well-established, recent works highlight their significant promise in other applications as well. One such area is traffic forecasting, where LLMs demonstrated the ability to generate powerful analytical insights, offering new opportunities for advancing Intelligent Transportation Systems (ITS). This survey summarizes 160 related works, providing a comprehensive review of methods, applications, and challenges. Specifically, we summarize the efforts to bridge the gap between time series data and language models, exploring their design principles and applications in various traffic scenarios, including traffic forecasting, traffic recommendation, mobility forecasting, urban management, signal control, and safety analysis. For deeper insights, we discuss existing challenges and highlight future research directions. This survey identifies three key limitations of current works: (1) LLM-based traffic models face practical deployment hurdles; (2) there lacks a unified benchmark across various applications; (3) resident privacy protection demands attention in their real-world applications. By providing a foundational understanding of LLMs for traffic forecasting, this survey aims to benefit not only the traffic mining community but also contribute to the broader advancement of Artificial General Intelligence (AGI).