11 papers
ChronoPhyBench: Do MLLMs Truly Understand the World or Merely Exploit Language Priors?
Bin Zhu, Yanhao Jia, Kexin Zhao +12
Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in open-world reasoning and understanding. However, a critical ambiguity pe…
Self-Debias: Self-correcting for Debiasing Large Language Models
Xuan Feng, Shuai Zhao, Luwei Xiao +2
Although Large Language Models (LLMs) demonstrate remarkable reasoning capabilities, inherent social biases often cascade throughout the Chain-of-Thought (CoT) process, leading to…
Towards Robust Evaluation of STEM Education: Leveraging MLLMs in Project-Based Learning
Xinyi Wu, Yanhao Jia, Qinglin Zhang +3
Project-Based Learning (PBL) involves a variety of highly correlated multimodal data, making it a vital educational approach within STEM disciplines. With the rapid development of…
P2P: A Poison-to-Poison Remedy for Reliable Backdoor Defense in LLMs
Shuai Zhao, Xinyi Wu, Shiqian Zhao +4
During fine-tuning, large language models (LLMs) are increasingly vulnerable to data-poisoning backdoor attacks, which compromise their reliability and trustworthiness. However, ex…
Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs
Man Hu, Xinyi Wu, Zuofeng Suo +5
With the rise of advanced reasoning capabilities, large language models (LLMs) are receiving increasing attention. However, although reasoning improves LLMs' performance on downstr…
DUP: Detection-guided Unlearning for Backdoor Purification in Language Models
Man Hu, Yahui Ding, Yatao Yang +3
As backdoor attacks become more stealthy and robust, they reveal critical weaknesses in current defense strategies: detection methods often rely on coarse-grained feature statistic…