Shihao Liu

Temporal Knowledge Graph Question Answering (TKGQA) aims to answer temporal questions using knowledge from Temporal Knowledge Graphs (TKGs).Existing LLM-based TKGQA methods typically utilize RAG-based or Agent-based paradigms, yet both struggle to construct reliable temporal evidence chains. RAG-...

Knowledge forgetting is a central challenge when adapting LLMs to new tasks. Prior studies indicate that pretrained knowledge is concentrated in the principal singular subspace of pretrained weight W_0 ; so recent Low-Rank Adaptation (LoRA) variants initialize LoRA in the minor subspace to steer...