STAR: Semantic-Tuned and Tail-Adaptive Retriever for Graph-Augmented Generation

• URL: http://arxiv.org/abs/2605.18765v1
• Date: Sat, 11 Apr 2026 10:16:51 GMT
• Title: STAR: Semantic-Tuned and Tail-Adaptive Retriever for Graph-Augmented Generation
• Abstract summary: We propose STAR, a semantic-tuned and tail-adaptive retriever for GraphRAG.<n> STAR consistently outperforms baselines, achieving average retrieval performance gains of 1.8%.
• Score: 69.66045538889777
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: To augment Large Language Models (LLMs) for multi-hop question answering, a mainstream solution within Graph Retrieval Augmented Generation (GraphRAG) leverages lightweight retrievers to efficiently extract information from a given Knowledge Graph (KG). However, existing methods often overlook the inherent challenge of sparse semantic information in graphs. Specifically, our experiments reveal that these methods produce biased retrieval Semantic Shortcut Bias and Long-Tail Path Bias, leading to inadequate semantic modeling and limited GraphRAG effectiveness. To address these issues, we propose STAR, a semantic-tuned and tail-adaptive retriever for GraphRAG. STAR integrates two key learning paradigms: token-level interaction learning and path-weighted contrastive learning. The former employs a cross-attention architecture and a hard path mining mechanism to jointly model the query and path, thereby mitigating the Semantic Shortcut Bias. The latter introduces a tailored contrastive learning objective that utilizes tail-adaptive path weighting, designed to optimize the training process and ease the Long-Tail Path Bias. Extensive experiments demonstrate that STAR consistently outperforms baselines, achieving average retrieval performance gains of 1.8\% and LLM QA performance improvements of 2.2\% across all benchmark datasets. Our code is available at https://anonymous.4open.science/r/STAR-C583.

Related papers

• Semi-supervised Instruction Tuning for Large Language Models on Text-Attributed Graphs [62.544129365882014]
  We propose a novel Semi-supervised Instruction Tuning pipeline for Graph Learning, named SIT-Graph.<n> SIT-Graph is model-agnostic and can be seamlessly integrated into any graph instruction tuning method that utilizes LLMs as the predictor.<n>Extensive experiments demonstrate that when incorporated into state-of-the-art graph instruction tuning methods, SIT-Graph significantly enhances their performance on text-attributed graph benchmarks.
  arXiv  Detail & Related papers  (2026-01-19T08:10:53Z)
• Reasoning by Exploration: A Unified Approach to Retrieval and Generation over Graphs [39.425801384830415]
  Reasoning over structured graphs remains a fundamental challenge for Large Language Models.<n>We propose Reasoning by Exploration (RoE), a novel approach that unifies retrieval and generation by framing reasoning over graphs as a process of graph exploration.<n>RoE achieves substantial overall improvements over baselines, while also generalizing effectively to unseen graphs.
  arXiv  Detail & Related papers  (2025-10-08T19:29:19Z)
• GRAIL:Learning to Interact with Large Knowledge Graphs for Retrieval Augmented Reasoning [13.481673780508215]
  GRAIL is a framework designed to interact with large-scale graphs for retrieval-augmented reasoning.<n>GRAIL achieves an average accuracy improvement of 21.01% and F1 improvement of 22.43% on knowledge graph question-answering datasets.
  arXiv  Detail & Related papers  (2025-08-07T15:34:41Z)
• GraphRunner: A Multi-Stage Framework for Efficient and Accurate Graph-Based Retrieval [3.792463570467098]
  GraphRunner is a novel graph-based retrieval framework that operates in three distinct stages: planning, verification, and execution.<n>It significantly reduces reasoning errors and detects hallucinations before execution.<n>Our evaluation using the GRBench dataset shows that GraphRunner consistently outperforms existing approaches.
  arXiv  Detail & Related papers  (2025-07-11T18:10:01Z)
• CLEAR: Cluster-based Prompt Learning on Heterogeneous Graphs [19.956925820094177]
  We present CLEAR, a Cluster-based prompt model on heterogeneous graphs.<n>We align the pretext and downstream tasks to share the same training objective.<n>Experiments on downstream tasks confirm the superiority of CLEAR.
  arXiv  Detail & Related papers  (2025-02-13T03:10:19Z)
• DiRW: Path-Aware Digraph Learning for Heterophily [34.32328516545247]
  graph neural network (GNN) has emerged as a powerful representation learning tool for graph-structured data.<n>DiRW is a plug-and-play strategy for most spatial-based DiGNNs and also an innovative model which offers a new digraph learning paradigm.<n>Experiments on 9 datasets demonstrate that DiRW: (1) enhances most spatial-based methods as a plug-and-play strategy; (2) SOTA performance as a new digraph learning paradigm.
  arXiv  Detail & Related papers  (2024-10-14T09:26:56Z)
• Efficient Heterogeneous Graph Learning via Random Projection [58.4138636866903]
  Heterogeneous Graph Neural Networks (HGNNs) are powerful tools for deep learning on heterogeneous graphs. Recent pre-computation-based HGNNs use one-time message passing to transform a heterogeneous graph into regular-shaped tensors. We propose a hybrid pre-computation-based HGNN, named Random Projection Heterogeneous Graph Neural Network (RpHGNN)
  arXiv  Detail & Related papers  (2023-10-23T01:25:44Z)
• SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning [131.04781590452308]
  We present SimTeG, a frustratingly Simple approach for Textual Graph learning. We first perform supervised parameter-efficient fine-tuning (PEFT) on a pre-trained LM on the downstream task. We then generate node embeddings using the last hidden states of finetuned LM.
  arXiv  Detail & Related papers  (2023-08-03T07:00:04Z)
• Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction [123.20238648121445]
  We propose a new self-supervised learning framework, Graph Information Aided Node feature exTraction (GIANT) GIANT makes use of the eXtreme Multi-label Classification (XMC) formalism, which is crucial for fine-tuning the language model based on graph information. We demonstrate the superior performance of GIANT over the standard GNN pipeline on Open Graph Benchmark datasets.
  arXiv  Detail & Related papers  (2021-10-29T19:55:12Z)
• Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking [58.30147362745852]
  Data association across frames is at the core of Multiple Object Tracking (MOT) task. Existing methods mostly ignore the context information among tracklets and intra-frame detections. We propose a novel learnable graph matching method to address these issues.
  arXiv  Detail & Related papers  (2021-03-30T08:58:45Z)

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.