# Query-Aware Learnable Graph Pooling Tokens as Prompt for Large Language Models Source: [Query-Aware Learnable Graph Pooling Tokens as Prompt for Large Language Models]() Collection index: [llms.txt]() Data updated: 2026-05-20T05:00:20.896Z Authors: Wooyoung Kim, Byungyoon Park, Wooju Kim Published: 2025-01-29T10:35:41.000Z ## Abstract Graph-structured data plays a vital role in numerous domains, such as social networks, citation networks, commonsense reasoning graphs and knowledge graphs. While graph neural networks have been employed for graph processing, recent advancements have explored integrating large language models for graph-based tasks. In this paper, we propose a novel approach named Learnable Graph Pooling Token (LGPT), which addresses the limitations of the scalability issues in node-level projection and information loss in graph-level projection. LGPT enables flexible and efficient graph representation by introducing learnable parameters that act as tokens in large language models, balancing fine-grained and global graph information. Additionally, we investigate an Early Query Fusion technique, which fuses query context before constructing the graph representation, leading to more effective graph embeddings. Our method achieves a 4.13\\% performance improvement on the GraphQA benchmark without training the large language model, demonstrating significant gains in handling complex textual-attributed graph data. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Graph Question Answering Suite (ExplaGraphs, SceneGraphs, WebQSP)](): Graph Question Answering; GraphQA ExplaGraphs, SceneGraphs, WebQSP; Expla Graphs Score: 90.07. ## Original sources and implementation [Original paper]() [PDF]()