Fine-tuning LLMs on graph tasks with a restricted attention window that includes partial graph links, then switching to a fully connected window at inference, improves node classification over standard full-attention fine-tuning.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Attention Mechanisms Perspective: Exploring LLM Processing of Graph-Structured Data
Fine-tuning LLMs on graph tasks with a restricted attention window that includes partial graph links, then switching to a fully connected window at inference, improves node classification over standard full-attention fine-tuning.