Publications (25)
Atomic Reasoning for Scientific Table Claim Verification
Yuji Zhang, Qingyun Wang, Cheng Qian +7
Scientific texts often convey authority due to their technical language and complex data. However, this complexity can sometimes lead to the spread of misinformation. Non-experts a…
VIBE: Topic-Driven Temporal Adaptation for Twitter Classification
Yuji Zhang, Jing Li, Wenjie Li
Language features are evolving in real-world social media, resulting in the deteriorating performance of text classification in dynamics. To address this challenge, we study tempor…
EMCompress: Video-LLMs with Endomorphic Multimodal Compression
Zheyu Fan, Jiateng Liu, Yuji Zhang +4
Video-LLMs face a fundamental tension in long-video reasoning: static, sparse frame sampling either dilutes evidence across task-irrelevant segments at significant cost or misses f…
Evolutionary Dynamics Based on Reputation in Networked Populations with Game Transitions
Yuji Zhang, Minyu Feng, Jürgen Kurths +1
The environment undergoes perpetual changes that are influenced by a combination of endogenous and exogenous factors. Consequently, it exerts a substantial influence on an individu…
Time Will Change Things: An Empirical Study on Dynamic Language Understanding in Social Media Classification
Yuji Zhang, Jing Li
Language features are ever-evolving in the real-world social media environment. Many trained models in natural language understanding (NLU), ineffective in semantic inference for u…
MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Models
Hyeonjeong Ha, Jeonghwan Kim, Cheng Qian +7
Memory-augmented large language models extend reasoning beyond a fixed context window by maintaining long-term memory across interactions. However, existing memory systems often co…
A Survey on the Honesty of Large Language Models
Siheng Li, Cheng Yang, Taiqiang Wu +12
Honesty is a fundamental principle for aligning large language models (LLMs) with human values, requiring these models to recognize what they know and don't know and be able to fai…
Geometric-disentangelment Unlearning
Duo Zhou, Yuji Zhang, Tianxin Wei +9
Large language models (LLMs) can internalize private or harmful content, motivating unlearning that removes a forget set while preserving retaining knowledge. However, forgetting u…
Agentic Reasoning for Large Language Models
Tianxin Wei, Ting-Wei Li, Zhining Liu +26
Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making. While large language models (LLMs) demonstrate strong reasoning capabilitie…
Evolutionary Cooperation with Game Transitions via Markov Decision Chain in Networked Population
Chaoyang Luo, Yuji Zhang, Minyu Feng +1
Individual cooperative strategy influences the surrounding dynamic population, which in turn affects cooperative strategy. To better model this phenomenon, we develop a Markov deci…
Integrative Decoding: Improve Factuality via Implicit Self-consistency
Yi Cheng, Xiao Liang, Yeyun Gong +11
Self-consistency-based approaches, which involve repeatedly sampling multiple outputs and selecting the most consistent one as the final response, prove to be remarkably effective…
Knowledge Graph-based Neurodegenerative Diseases and Diet Relationship Discovery
Yi Nian, Jingcheng Du, Larry Bu +4
To date, there are no effective treatments for most neurodegenerative diseases. However, certain foods may be associated with these diseases and bring an opportunity to prevent or…
Event-Enhanced Multi-Modal Spiking Neural Network for Dynamic Obstacle Avoidance
Yang Wang, Bo Dong, Yuji Zhang +4
Autonomous obstacle avoidance is of vital importance for an intelligent agent such as a mobile robot to navigate in its environment. Existing state-of-the-art methods train a spiki…
ShortageSim: Simulating Drug Shortages under Information Asymmetry
Mingxuan Cui, Yilan Jiang, Duo Zhou +3
Drug shortages pose critical risks to patient care and healthcare systems worldwide, yet the effectiveness of regulatory interventions remains poorly understood due to information…
ModelingAgent: Bridging LLMs and Mathematical Modeling for Real-World Challenges
Cheng Qian, Hongyi Du, Hongru Wang +6
Recent progress in large language models (LLMs) has enabled substantial advances in solving mathematical problems. However, existing benchmarks often fail to reflect the complexity…
Effects of Stochastic Games on Evolutionary Dynamics in Structured Populations
Yuji Zhang, Minyu Feng, Qin Li +2
Continuously changing environments have a paramount role in the evolution of cooperative behavior. Previous works have shown that the transitions among different games, as the feed…
The Law of Knowledge Overshadowing: Towards Understanding, Predicting, and Preventing LLM Hallucination
Yuji Zhang, Sha Li, Cheng Qian +8
Hallucination is a persistent challenge in large language models (LLMs), where even with rigorous quality control, models often generate distorted facts. This paradox, in which err…
SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals
Peixuan Han, Cheng Qian, Xiusi Chen +3
Large language models (LLMs) exhibit exceptional capabilities across various tasks but also pose risks by generating harmful content. Existing safety mechanisms, while improving mo…
EscapeBench: Towards Advancing Creative Intelligence of Language Model Agents
Cheng Qian, Peixuan Han, Qinyu Luo +9
Language model agents excel in long-session planning and reasoning, but existing benchmarks primarily focus on goal-oriented tasks with explicit objectives, neglecting creative ada…
TAMA: A Human-AI Collaborative Thematic Analysis Framework Using Multi-Agent LLMs for Clinical Interviews
Huimin Xu, Seungjun Yi, Terence Lim +9
Thematic analysis (TA) is a widely used qualitative approach for uncovering latent meanings in unstructured text data. TA provides valuable insights in healthcare but is resource-i…
Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models
Yuji Zhang, Sha Li, Jiateng Liu +5
Hallucination is often regarded as a major impediment for using large language models (LLMs), especially for knowledge-intensive tasks. Even when the training corpus consists solel…
EVEDIT: Event-based Knowledge Editing with Deductive Editing Boundaries
Jiateng Liu, Pengfei Yu, Yuji Zhang +3
The dynamic nature of real-world information necessitates efficient knowledge editing (KE) in large language models (LLMs) for knowledge updating. However, current KE approaches, w…
Current Agents Fail to Leverage World Model as Tool for Foresight
Cheng Qian, Emre Can Acikgoz, Bingxuan Li +8
Agents built on vision-language models increasingly face tasks that demand anticipating future states rather than relying on short-horizon reasoning. Generative world models offer…
Payoff-Driven Coevolution and Oscillatory Dynamics in Hypergraph
Yichao Yao, Yuji Zhang, Juan Wu +2
We study a coevolutionary public goods game on a dynamic hypergraph, where an individual's payoff directly determines the number of hyperedges it can join. In the proposed mechanis…
Benchmarking Multi-turn Medical Diagnosis: Hold, Lure, and Self-Correction
Jinrui Fang, Runhan Chen, Xu Yang +9
Large language models (LLMs) achieve high accuracy in medical diagnosis when all clinical information is provided in a single turn, yet how they behave under multi-turn evidence ac…