5 papers
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…
Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggers
Jiali Wei, Ming Fan, Guoheng Sun +3
The growing application of large language models (LLMs) in safety-critical domains has raised urgent concerns about their security. Many recent studies have demonstrated the feasib…
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.…
LLM-Driven Self-Refinement for Embodied Drone Task Planning
Deyu Zhang, Xicheng Zhang, Jiahao Li +6
We introduce SRDrone, a novel system designed for self-refinement task planning in industrial-grade embodied drones. SRDrone incorporates two key technical contributions: First, it…
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…