5 citations · 5 across the 5 of their papers we have counts for
6 papers
Not All Tokens Are Equal: Region-Aware Consistency Repair of Backdoors in MLLMs
Jiali Wei, Ming Fan, Mingkun Zhang +6
MLLMs are increasingly deployed in user-facing applications, yet they inherit backdoor risks from the pipelines used to construct them: triggers may reside in images, texts, or bot…
DAIS: Dependency-Aware Intermediate QA Supervision for Complex Reasoning
Yu Wang, Ming Fan, Xicheng Zhang +5
Chain-of-thought (CoT) supervision exposes intermediate rationales, but flat rationale targets usually optimize a single reasoning sequence and provide limited supervision on how l…
RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoning
Yu Wang, Shiwan Zhao, Zhihu Wang +6
The integration of external knowledge through Retrieval-Augmented Generation (RAG) has become foundational in enhancing large language models (LLMs) for knowledge-intensive tasks.…
Separator Injection Attack: Uncovering Dialogue Biases in Large Language Models Caused by Role Separators
Xitao Li, Haijun Wang, Jiang Wu +1
Conversational large language models (LLMs) have gained widespread attention due to their instruction-following capabilities. To ensure conversational LLMs follow instructions, rol…
Stealthy Backdoor Attack to Real-world Models in Android Apps
Jiali Wei, Ming Fan, Xicheng Zhang +3
Powered by their superior performance, deep neural networks (DNNs) have found widespread applications across various domains. Many deep learning (DL) models are now embedded in mob…
Strategic Chain-of-Thought: Guiding Accurate Reasoning in LLMs through Strategy Elicitation
Yu Wang, Shiwan Zhao, Zhihu Wang +6
The Chain-of-Thought (CoT) paradigm has emerged as a critical approach for enhancing the reasoning capabilities of large language models (LLMs). However, despite their widespread a…