9 papers
CARA: Exact Local Repair with Fresh One-Action Certification for Cloud Consolidation
Xiyang Zhang, Yuanhe Tian, Hongzhi Wang
Simulator-based placement pipelines may inspect many repairs but deploy only when several reliability criteria improve together. Reusing search scenes to test the selected action i…
ALIVE: Warnings Before Exclusion in Budgeted Multi-Source Learning
Xiyang Zhang, Hongzhi Wang, Yuanhe Tian
A routing decision can be revised at the next transaction, but a latched source exclusion persists across later decisions. We ask what evidence should authorize these unequal-persi…
Composition Collapse: Stable Factual Knowledge Does Not Imply Compositional Reasoning
Zhe Yu, Wenpeng Xing, Yunzhao Wei +4
Post-training is routinely evaluated through aggregate benchmark scores that treat multi-hop reasoning as a single capability -- as if a model that answers more questions correctly…
Cordon-MAS: Defending RAG against Knowledge Poisoning via Information-Flow Control
Zhe Yu, Wenpeng Xing, Gaolei Li +4
Retrieval-augmented generation (RAG) increasingly underpins high-stakes applications, yet remains vulnerable to Confundo-style poisoning where adversarially optimized documents man…
HART: Data-Driven Hallucination Attribution and Evidence-Based Tracing for Large Language Models
Shize Liang, Hongzhi Wang
Large language models (LLMs) have demonstrated remarkable performance in text generation and knowledge-intensive question answering. Nevertheless, they are prone to producing hallu…
Training Data Selection with Gradient Orthogonality for Efficient Domain Adaptation
Xiyang Zhang, Yuanhe Tian, Hongzhi Wang +1
Fine-tuning large language models (LLMs) for specialized domains often necessitates a trade-off between acquiring domain expertise and retaining general reasoning capabilities, a p…