Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models

• URL: http://arxiv.org/abs/2506.07334v1
• Date: Mon, 09 Jun 2025 00:30:08 GMT
• Title: Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models
• Authors: Haoyu Wang, Peihao Wang, Mufei Li, Shikun Liu, Siqi Miao, Zhangyang Wang, Pan Li,
• Abstract summary: We introduce Graph-KV, which governs interaction through structural inductive biases.<n>In this framework, 'target' segments selectively attend only to the KV-cache of their designated'source' segments.<n>We evaluate Graph-KV across three scenarios: (1) seven RAG benchmarks spanning direct inference, multi-hop reasoning, and long-document understanding; (2) Arxiv-QA, a novel academic paper QA task with full-text scientific papers structured as citation ego-graphs; and (3) paper topic classification within a citation network.
• Score: 63.64507678113921
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern large language models (LLMs) are inherently auto-regressive, requiring input to be serialized into flat sequences regardless of their structural dependencies. This serialization hinders the model's ability to leverage structural inductive biases, especially in tasks such as retrieval-augmented generation (RAG) and reasoning on data with native graph structures, where inter-segment dependencies are crucial. We introduce Graph-KV with the potential to overcome this limitation. Graph-KV leverages the KV-cache of text segments as condensed representations and governs their interaction through structural inductive biases. In this framework, 'target' segments selectively attend only to the KV-caches of their designated 'source' segments, rather than all preceding segments in a serialized sequence. This approach induces a graph-structured block mask, sparsifying attention and enabling a message-passing-like step within the LLM. Furthermore, strategically allocated positional encodings for source and target segments reduce positional bias and context window consumption. We evaluate Graph-KV across three scenarios: (1) seven RAG benchmarks spanning direct inference, multi-hop reasoning, and long-document understanding; (2) Arxiv-QA, a novel academic paper QA task with full-text scientific papers structured as citation ego-graphs; and (3) paper topic classification within a citation network. By effectively reducing positional bias and harnessing structural inductive biases, Graph-KV substantially outperforms baselines, including standard costly sequential encoding, across various settings. Code and the Graph-KV data are publicly available.

Related papers

• Integrating Structural and Semantic Signals in Text-Attributed Graphs with BiGTex [0.16385815610837165]
  BiGTex is a novel architecture that tightly integrates GNNs and LLMs through stacked Graph-Text Fusion Units.<n>BiGTex achieves state-of-the-art performance in node classification and generalizes effectively to link prediction.
  arXiv  Detail & Related papers  (2025-04-16T20:25:11Z)
• Scale-Free Graph-Language Models [44.283149785253286]
  Graph-language models (GLMs) have demonstrated great potential in graph-based semi-supervised learning.<n>This paper introduces a novel GLM that integrates graph generation and text embedding within a unified framework.
  arXiv  Detail & Related papers  (2025-02-21T03:41:43Z)
• Beyond Message Passing: Neural Graph Pattern Machine [50.78679002846741]
  We introduce the Neural Graph Pattern Machine (GPM), a novel framework that bypasses message passing by learning directly from graph substructures.<n>GPM efficiently extracts, encodes, and prioritizes task-relevant graph patterns, offering greater expressivity and improved ability to capture long-range dependencies.
  arXiv  Detail & Related papers  (2025-01-30T20:37:47Z)
• GraphCroc: Cross-Correlation Autoencoder for Graph Structural Reconstruction [6.817416560637197]
  Graph autoencoders (GAEs) reconstruct graph structures from node embeddings. We introduce a cross-correlation mechanism that significantly enhances the GAE representational capabilities. We also propose GraphCroc, a new GAE that supports flexible encoder architectures tailored for various downstream tasks.
  arXiv  Detail & Related papers  (2024-10-04T12:59:45Z)
• Learning to Model Graph Structural Information on MLPs via Graph Structure Self-Contrasting [50.181824673039436]
  We propose a Graph Structure Self-Contrasting (GSSC) framework that learns graph structural information without message passing. The proposed framework is based purely on Multi-Layer Perceptrons (MLPs), where the structural information is only implicitly incorporated as prior knowledge. It first applies structural sparsification to remove potentially uninformative or noisy edges in the neighborhood, and then performs structural self-contrasting in the sparsified neighborhood to learn robust node representations.
  arXiv  Detail & Related papers  (2024-09-09T12:56:02Z)
• A Pure Transformer Pretraining Framework on Text-attributed Graphs [50.833130854272774]
  We introduce a feature-centric pretraining perspective by treating graph structure as a prior. Our framework, Graph Sequence Pretraining with Transformer (GSPT), samples node contexts through random walks. GSPT can be easily adapted to both node classification and link prediction, demonstrating promising empirical success on various datasets.
  arXiv  Detail & Related papers  (2024-06-19T22:30:08Z)
• Deep Contrastive Graph Learning with Clustering-Oriented Guidance [61.103996105756394]
  Graph Convolutional Network (GCN) has exhibited remarkable potential in improving graph-based clustering. Models estimate an initial graph beforehand to apply GCN. Deep Contrastive Graph Learning (DCGL) model is proposed for general data clustering.
  arXiv  Detail & Related papers  (2024-02-25T07:03:37Z)
• Graph Language Models [18.75364157933661]
  We introduce a novel LM type, the Graph Language Model (GLM), that integrates the strengths of both approaches and mitigates their weaknesses. We design the GLM's architecture to incorporate graph biases, thereby promoting effective knowledge distribution within the graph. Empirical evaluations on relation classification tasks show that GLM embeddings surpass both LM- and GNN-based baselines in supervised and zero-shot setting.
  arXiv  Detail & Related papers  (2024-01-13T16:09:49Z)
• LAGr: Labeling Aligned Graphs for Improving Systematic Generalization in Semantic Parsing [6.846638912020957]
  We show that better systematic generalization can be achieved by producing the meaning representation directly as a graph and not as a sequence. We propose LAGr, the Labeling Aligned Graphs algorithm that produces semantic parses by predicting node and edge labels for a complete multi-layer input-aligned graph.
  arXiv  Detail & Related papers  (2021-10-14T17:37:04Z)
• GraphiT: Encoding Graph Structure in Transformers [37.33808493548781]
  We show that viewing graphs as sets of node features and structural and positional information is able to outperform representations learned with classical graph neural networks (GNNs) Our model, GraphiT, encodes such information by (i) leveraging relative positional encoding strategies in self-attention scores based on positive definite kernels on graphs, and (ii) enumerating and encoding local sub-structures such as paths of short length.
  arXiv  Detail & Related papers  (2021-06-10T11:36:22Z)
• Structure-Augmented Text Representation Learning for Efficient Knowledge Graph Completion [53.31911669146451]
  Human-curated knowledge graphs provide critical supportive information to various natural language processing tasks. These graphs are usually incomplete, urging auto-completion of them. graph embedding approaches, e.g., TransE, learn structured knowledge via representing graph elements into dense embeddings. textual encoding approaches, e.g., KG-BERT, resort to graph triple's text and triple-level contextualized representations.
  arXiv  Detail & Related papers  (2020-04-30T13:50:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.