3 papers
cs.LG2026
Recipe-Controlled Decoder Audit for Structural Knowledge-Graph Completion
Xihang Shan, Ye Luo
We present a recipe-controlled decoder audit (RCDA) for structural transductive knowledge-graph completion (KGC). The audit asks a simple reporting question: before attributing gai…
cs.CL2026
Bounded Path Context: A Controlled Study of Visible Path History in LLM-Based Knowledge Graph Question Answering
Xihang Shan, Ye Luo
LLM-based knowledge-graph question answering (KGQA) delegates graph traversal to language models, turning each question into a sequence of local relation-selection decisions repeat…
stat.ML2026
PRCD-MAP: Learning How Much to Trust Imperfect Priors in Causal Discovery
Xihang Shan, Da Zhou
External priors of unknown reliability create a brittle trade-off in causal discovery: blind trust amplifies errors, blind rejection wastes signal. Real priors are also heterogeneo…