4 papers
Diagnosing Sampled LLM Reasoning in Formal Geometry: Coverage, Realization, and Validity Evidence
Xiao Yue, Guangzhi Qu
Repeated sampling can reveal a correct numerical answer without yielding either a reliable system output or a supported derivation. We present Coverage, Realization, and Validity E…
When Does Explicit View Routing Work? A Controlled Study of Multi-View Graph-Text Alignment
Xiao Yue, Guangzhi Qu
Graph-text retrieval typically maps a graph and its description to a single embedding, even when a query concerns only one semantic aspect, such as a class label or molecular prope…
LiteSemRAG: Lightweight LLM-Free Semantic-Aware Graph Retrieval for Robust RAG
Xiao Yue, Guangzhi Qu, Lige Gan
Graph-based Retrieval-Augmented Generation (RAG) has shown great potential for improving multi-level reasoning and structured evidence aggregation. However, existing graph-based RA…
GIN-Graph: A Generative Interpretation Network for Model-Level Explanation of Graph Neural Networks
Xiao Yue, Guangzhi Qu, Lige Gan
One significant challenge of exploiting Graph neural networks (GNNs) in real-life scenarios is that they are always treated as black boxes, therefore leading to the requirement of…