12 citations · 40 across the 20 of their papers we have counts for
21 papers
BeliefGraph-JEPA: Structured Latent World Models for Action-Conditioned Time Series
Yue Li, Kangqi Ni, Zhen Tan +1
Action-conditioned time-series forecasting requires accounting for how future actions and exogenous forcings influence multiple targets through partially observed effects with diff…
Intrinsic Barriers to Explaining Deep Foundation Models
Zhen Tan, Huan Liu
Deep Foundation Models (DFMs) offer unprecedented capabilities but their increasing complexity presents profound challenges to understanding their internal workings-a critical need…
Visual Large Language Models for Generalized and Specialized Applications
Yifan Li, Zhixin Lai, Wentao Bao +7
Visual-language models (VLM) have emerged as a powerful tool for learning a unified embedding space for vision and language. Inspired by large language models, which have demonstra…
CAND: Cross-Domain Ambiguity Inference for Early Detecting Nuanced Illness Deterioration
Lo Pang-Yun Ting, Zhen Tan, Hong-Pei Chen +4
Early detection of patient deterioration is essential for timely treatment, with vital signs like heart rates being key health indicators. Existing methods tend to solely analyze v…
Assessing the Impact of Conspiracy Theories Using Large Language Models
Bohan Jiang, Dawei Li, Zhen Tan +5
Measuring the relative impact of CTs is important for prioritizing responses and allocating resources effectively, especially during crises. However, assessing the actual impact of…
From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge
Dawei Li, Bohan Jiang, Liangjie Huang +10
Assessment and evaluation have long been critical challenges in artificial intelligence (AI) and natural language processing (NLP). Traditional methods, usually matching-based or s…
Can LLMs Improve Multimodal Fact-Checking by Asking Relevant Questions?
Alimohammad Beigi, Bohan Jiang, Dawei Li +5
Traditional fact-checking relies on humans to formulate relevant and targeted fact-checking questions (FCQs), search for evidence, and verify the factuality of claims. While Large…
Model Attribution in LLM-Generated Disinformation: A Domain Generalization Approach with Supervised Contrastive Learning
Alimohammad Beigi, Zhen Tan, Nivedh Mudiam +3
Model attribution for LLM-generated disinformation poses a significant challenge in understanding its origins and mitigating its spread. This task is especially challenging because…
Exploring Large Language Models for Feature Selection: A Data-centric Perspective
Dawei Li, Zhen Tan, Huan Liu
The rapid advancement of Large Language Models (LLMs) has significantly influenced various domains, leveraging their exceptional few-shot and zero-shot learning capabilities. In th…
"Glue pizza and eat rocks" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Models
Zhen Tan, Chengshuai Zhao, Raha Moraffah +5
Retrieval-Augmented Generative (RAG) models enhance Large Language Models (LLMs) by integrating external knowledge bases, improving their performance in applications like fact-chec…
Catching Chameleons: Detecting Evolving Disinformation Generated using Large Language Models
Bohan Jiang, Chengshuai Zhao, Zhen Tan +1
Despite recent advancements in detecting disinformation generated by large language models (LLMs), current efforts overlook the ever-evolving nature of this disinformation. In this…
Facial Affective Behavior Analysis with Instruction Tuning
Yifan Li, Anh Dao, Wentao Bao +4
Facial affective behavior analysis (FABA) is crucial for understanding human mental states from images. However, traditional approaches primarily deploy models to discriminate amon…
Media Bias Matters: Understanding the Impact of Politically Biased News on Vaccine Attitudes in Social Media
Bohan Jiang, Lu Cheng, Zhen Tan +2
News media has been utilized as a political tool to stray from facts, presenting biased claims without evidence. Amid the COVID-19 pandemic, politically biased news (PBN) has signi…
GraphRCG: Self-Conditioned Graph Generation
Song Wang, Zhen Tan, Xinyu Zhao +3
Graph generation generally aims to create new graphs that closely align with a specific graph distribution. Existing works often implicitly capture this distribution through the op…
Contextualization Distillation from Large Language Model for Knowledge Graph Completion
Dawei Li, Zhen Tan, Tianlong Chen +1
While textual information significantly enhances the performance of pre-trained language models (PLMs) in knowledge graph completion (KGC), the static and noisy nature of existing…
The Wolf Within: Covert Injection of Malice into MLLM Societies via an MLLM Operative
Zhen Tan, Chengshuai Zhao, Raha Moraffah +4
Due to their unprecedented ability to process and respond to various types of data, Multimodal Large Language Models (MLLMs) are constantly defining the new boundary of Artificial…
Sparsity-Guided Holistic Explanation for LLMs with Interpretable Inference-Time Intervention
Zhen Tan, Tianlong Chen, Zhenyu Zhang +1
Large Language Models (LLMs) have achieved unprecedented breakthroughs in various natural language processing domains. However, the enigmatic ``black-box'' nature of LLMs remains a…
CSGNN: Conquering Noisy Node labels via Dynamic Class-wise Selection
Yifan Li, Zhen Tan, Kai Shu +3
Graph Neural Networks (GNNs) have emerged as a powerful tool for representation learning on graphs, but they often suffer from overfitting and label noise issues, especially when t…
Interpreting Pretrained Language Models via Concept Bottlenecks
Zhen Tan, Lu Cheng, Song Wang +3
Pretrained language models (PLMs) have made significant strides in various natural language processing tasks. However, the lack of interpretability due to their ``black-box'' natur…
Noise-Robust Fine-Tuning of Pretrained Language Models via External Guidance
Song Wang, Zhen Tan, Ruocheng Guo +1
Adopting a two-stage paradigm of pretraining followed by fine-tuning, Pretrained Language Models (PLMs) have achieved substantial advancements in the field of natural language proc…
Graph Few-shot Class-incremental Learning
Zhen Tan, Kaize Ding, Ruocheng Guo +1
The ability to incrementally learn new classes is vital to all real-world artificial intelligence systems. A large portion of high-impact applications like social media, recommenda…