Question-Adaptive Graph Learning for Multi-hop Retrieval Augmented Generation
sigir26-169 · Full research paper · Yuchen Yan, Peiyan Zhang, Zhihua Liu, Hao Wang, Yatao Bian, Weiming Li, Xiaoshuai Hao
KG-Augmented LLM Reasoning · 50% Multi-Hop and Iterative Retrieval Re · 25% Multimodal and Graph RAG · 25%
Abstract
Retrieval-augmented generation (RAG) has demonstrated its ability to enhance Large Language Models (LLMs) by integrating external knowledge sources. However, multi-hop questions, which require the identification of multiple knowledge targets to form a synthesized answer, raise new challenges for RAG systems. Under the multi-hop settings, existing methods often struggle to fully understand the questions with complex semantic structures and are susceptible to irrelevant noise during the retrieval of multiple information targets. To address these limitations, we propose a novel graph representation learning framework for multi-hop question retrieval. We first introduce a Multi-information Level Knowledge Graph (Multi-L KG) to model various information levels for a more comprehensive understanding of multi-hop questions. Based on this, we design a Question-Adaptive Graph Neural Network (Quest-GNN) for representation learning on the Multi-L KG. Quest-GNN employs intra/inter-level message passing mechanisms, and in each message passing the information aggregation is guided by the question, which not only facilitates multi-granular information aggregation but also significantly reduces the impact of noise. To enhance its ability to learn robust representations, we further propose two synthesized data generation strategies for pre-training the Quest-GNN. Extensive experimental results demonstrate the effectiveness of our framework in multi-hop scenarios, especially in high-hop questions the improvement can reach 33.8%. The code is available at: https://github.com/Jerry2398/QSGNN.
Assigned reviewers
| # | Reviewer | Match | Why (closest evidence publications in the taxonomy) | |
|---|---|---|---|---|
| 1 | Xingyu Tan 0001 | 85 | 100 HydraRAG: Structured Cross-Source Enhanced Large Language Model Reasoning (2025) KG-Augmented LLM Reasoning 100 Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning (2025) KG-Augmented LLM Reasoning 100 MemoTime: Memory-Augmented Temporal Knowledge Graph Enhanced Large Language Model Reasoning (2026) KG-Augmented LLM Reasoning |
|
| 2 | Farzad Shami | 64 | 68 Benchmarking Large Language Models for Knowledge Graph Validation (2026) KG-Augmented LLM Reasoning 68 Fact Verification in Knowledge Graphs Using LLMs (2025) KG-Augmented LLM Reasoning 43 From Single to Multi-agent Reasoning: Advancing GeneGPT for Genomics QA (2026) Retrieval-Augmented and Open-Domain QA |
|
| 3 | Armin Toroghi | 59 | 71 CommonWhy: A Dataset for Evaluating Entity-Based Causal Commonsense Reasoning in Large Language Models (2026) Knowledge Graph Question Answering 68 LLM-based Typed Hyperresolution for Commonsense Reasoning with Knowledge Bases (2025) KG-Augmented LLM Reasoning 68 Verifiable, Debuggable, and Repairable Commonsense Logical Reasoning via LLM-based Theory Resolution (2024) KG-Augmented LLM Reasoning |
Area chair
| Area chair | Match | |
|---|---|---|
| Hongjin Qian | 42 |
Area-chair candidates (4)
| Xiaoxi Li 0005 COI: co-author | 43 | 15 papers | |
| Hongjin Qian assigned | 42 | 12 papers | |
| Zhijing Wu 0001 COI: co-author | 40 | 9 papers | |
| Jun Xu 0001 | 37 | 2 papers |
Candidates from the panel ranked by match score
| # | Reviewer | Match | Load | Why | |
|---|---|---|---|---|---|
| 1 | Xingyu Tan 0001 assigned | 85 | 3 | 100 HydraRAG: Structured Cross-Source Enhanced Large Language Model Reasoning (2025) KG-Augmented LLM Reasoning 100 Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning (2025) KG-Augmented LLM Reasoning |
|
| 2 | Farzad Shami assigned | 64 | 3 | 68 Benchmarking Large Language Models for Knowledge Graph Validation (2026) KG-Augmented LLM Reasoning 68 Fact Verification in Knowledge Graphs Using LLMs (2025) KG-Augmented LLM Reasoning |
|
| 3 | Armin Toroghi assigned | 59 | 3 | 71 CommonWhy: A Dataset for Evaluating Entity-Based Causal Commonsense Reasoning in Large Language Models (2026) Knowledge Graph Question Answering 68 LLM-based Typed Hyperresolution for Commonsense Reasoning with Knowledge Bases (2025) KG-Augmented LLM Reasoning |
|
| 4 | Qinggang Zhang | 51 | 3 | 87 KnowGPT: Knowledge Graph based Prompting for Large Language Models (2024) Multimodal and Graph RAG 68 You Don't Need Pre-Built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures (2026) Multi-Hop and Iterative Retrieval Reasoning |
|
| 5 | Jiapu Wang | 51 | 3 | 67 Unifying Large Language Models and Knowledge Graphs: A Roadmap (2024) KG-Augmented LLM Reasoning 67 From implicit parameters to explicit knowledge graphs: A structured knowledge recall framework for bidirectional generalization in LLMs (2027) KG-Augmented LLM Reasoning |
|
| 6 | Yu Gu 0016 | 49 | 3 | 100 HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models (2024) KG-Augmented LLM Reasoning 67 Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments (2024) KG-Augmented LLM Reasoning |
|
| 7 | Xinying Qian | 48 | 3 | 88 TimeR⁴ : Time-aware Retrieval-Augmented Large Language Models for Temporal Knowledge Graph Question Answering (2024) Multi-Hop and Iterative Retrieval Reasoning 44 Beyond Timestamps: Bridging Forward and Backward Reasoning in Temporal Numerical and Relational Understanding (2026) Multi-hop and Complex Reasoning QA |
|
| 8 | Wenyu Huang | 46 | 3 | 75 Prompting large language models with knowledge graphs for question answering involving long-tail facts (2025) KG-Augmented LLM Reasoning 44 Masking in Multi-hop QA: An Analysis of How Language Models Perform with Context Permutation (2025) Multi-hop and Complex Reasoning QA |
|
| 9 | Xiaolong Jin 0001 | 45 | 3 | 68 A New Pipeline for Knowledge Graph Reasoning Enhanced by Large Language Models Without Fine-Tuning (2024) KG-Augmented LLM Reasoning 46 Hierarchical Query Graph Generation for Complex Question Answering over Knowledge Graph (2020) Knowledge Graph Question Answering |
|
| 10 | Jinheon Baek | 45 | 3 | 63 KALA: Knowledge-Augmented Language Model Adaptation (2022) KG-Augmented LLM Reasoning 54 Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity (2024) Multi-Hop and Iterative Retrieval Reasoning |
|
| 11 | Ben Liu 0002 | 45 | 3 | 55 SymAgent: A Neural-Symbolic Self-Learning Agent Framework for Complex Reasoning over Knowledge Graphs (2025) Reasoning Evaluation and Benchmarks 55 Plan Then Retrieve: Reinforcement Learning-Guided Complex Reasoning over Knowledge Graphs (2026) RL Training of Search Agents |
|
| 12 | Yuzhong Qu | 44 | 3 | 49 Enhancing Complex Question Answering over Knowledge Graphs through Evidence Pattern Retrieval (2024) Knowledge Graph Question Answering 49 Skeleton parsing for complex question answering over knowledge bases (2022) Knowledge Graph Question Answering |
|
| 14 | Shu Zhou 0002 COI: co-author | 43 | 3 | 88 DynKGRAG: A framework for dynamic knowledge graph construction and multi-hop querying over numerical and textual data (2026) Multi-Hop and Iterative Retrieval Reasoning 55 SCORE-RAG: Self-Correcting Exploration-Exploitation Retrieval for Multi-hop Question Answering (2026) Multi-Hop and Iterative Retrieval Reasoning |
|
| 15 | Tianzhe Zhao | 43 | 3 | 53 Logic-Aware Knowledge Graph Reasoning for Structural Sparsity under Large Language Model Supervision (2025) Graph Learning for Text-Attributed and Heterogeneous Networks 51 Self-supervised Quantized Representation for Seamlessly Integrating Knowledge Graphs with Large Language Models (2025) Text Representation and Language Models › Others |
|
| 16 | Navve Wasserman | 42 | 3 | 47 DocReRank: Single-Page Hard Negative Query Generation for Training Multi-Modal RAG Rerankers (2025) Universal Multimodal Embedding and MLLM Retrieval 47 REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark (2025) Universal Multimodal Embedding and MLLM Retrieval |
|
| 17 | Xuhui Sui | 42 | 3 | 70 TimeR⁴ : Time-aware Retrieval-Augmented Large Language Models for Temporal Knowledge Graph Question Answering (2024) RL Training of Search Agents 41 Dark Side of Modalities: Reinforced Multimodal Distillation for Multimodal Knowledge Graph Reasoning (2025) Knowledge Graph Embedding and Completion |
|
| 18 | Kaixin Ma | 42 | 3 | 61 Knowledge-driven Data Construction for Zero-shot Evaluation in Commonsense Question Answering (2021) Retrieval-Augmented and Open-Domain QA 56 Open Domain Question Answering with A Unified Knowledge Interface (2022) Multimodal and Graph RAG |
|
| 20 | Jimeng Sun 0001 | 41 | 3 | 87 MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models (2024) Multimodal and Graph RAG 86 A Survey on Unifying Large Language Models and Knowledge Graphs for Biomedicine and Healthcare (2025) KG-Augmented LLM Reasoning |
|
| 21 | Chen Zhao 0013 | 40 | 3 | 57 SportReason: Evaluating Retrieval-Augmented Reasoning across Tables and Text for Sports Question Answering (2025) Multi-Hop and Iterative Retrieval Reasoning 44 TaPERA: Enhancing Faithfulness and Interpretability in Long-Form Table QA by Content Planning and Execution-based Reasoning (2024) Multi-hop and Complex Reasoning QA |
|
| 23 | Wonduk Seo | 40 | 3 | 39 A New Query Expansion Approach for Enhancing Information Retrieval via Agent-Mediated Dialogic Inquiry (2026) Query Reformulation and Expansion 37 Question-to-Knowledge (Q2K): Multi-Agent Generation of Inspectable Facts for Product Mapping (2025) Entity Linking and Alignment |
|
| 24 | Xiangyu Ke | 39 | 3 | 56 An Interactive Multi-modal Query Answering System with Retrieval-Augmented Large Language Models (2024) Multimodal and Graph RAG 41 Academic Expert Finding via $(k, \mathcal{P})$-Core based Embedding over Heterogeneous Graphs (2022) Knowledge Graph Embedding and Completion |
|
| 25 | Di Wu 0054 | 38 | 3 | 46 VisRet: Visualization Improves Knowledge-Intensive Text-to-Image Retrieval (2026) Multimodal and Graph RAG 44 Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented Generation (2024) Knowledge Conflict and Faithfulness |
|
| 26 | Archiki Prasad | 38 | 3 | 44 AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge (2025) Knowledge Conflict and Faithfulness 43 MeetingQA: Extractive Question-Answering on Meeting Transcripts (2023) Retrieval-Augmented and Open-Domain QA |
|
| 27 | Fu Zhang 0001 | 38 | 3 | 41 A self-supervised method for learning path-augmented knowledge graph embedding (2025) Knowledge Graph Embedding and Completion 41 Representation Learning of Knowledge Graphs with Multi-scale Capsule Network (2019) Knowledge Graph Embedding and Completion |
|
| 28 | Qingyi Si | 38 | 3 | 44 Breaking the Trade-Off Between Faithfulness and Expressiveness for Large Language Models (2026) Knowledge Conflict and Faithfulness 44 Cross-modality Multiple Relations Learning for Knowledge-based Visual Question Answering (2024) Knowledge Graph Question Answering |
|
| 29 | Weiwei Sun 0001 | 38 | 3 | 44 Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models (2026) Evidence Selection and Context Refinement 44 Contrastive Learning Reduces Hallucination in Conversations (2023) Knowledge Conflict and Faithfulness |
|
| 30 | Mariano Barone | 38 | 3 | 42 Combining Evidence and Reasoning for Biomedical Fact-Checking (2025) Automated Fact Checking and Claim Verification 41 Combating Biomedical Misinformation through Multi-modal Claim Detection and Evidence-based Verification (2025) RAG for Domain Applications |
|
| 31 | Dan Luo 0004 | 38 | 3 | 68 PAGER: Proactive Monitoring Agent for Enterprise AI Assistant (2026) Reasoning Evaluation and Benchmarks 63 From Anchors to Answers: A Novel Node Tokenizer for Integrating Graph Structure into Large Language Models (2025) KG-Augmented LLM Reasoning |
|
| 32 | Idan Szpektor | 38 | 3 | 44 DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering (2023) Knowledge Conflict and Faithfulness 43 SIGIR 2016 Workshop WebQA II: Web Question Answering Beyond Factoids (2016) Retrieval-Augmented and Open-Domain QA |
|
| 33 | Jialong Wu 0007 | 38 | 3 | 42 WebWalker: Benchmarking LLMs in Web Traversal (2025) Agentic and Deep Search RAG 39 AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignment (2025) Query Reformulation and Expansion |