mlsanityData to 14 Oct 2026

GrapeQA: GRaph Augmentation and Pruning to Enhance Question-Answering

arXiv 2303.12320 ↗First posted 22 Mar 2023cs.CLcited by 17

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Commonsense question-answering (QA) methods combine the power of pre-trained Language Models (LM) with the reasoning provided by Knowledge Graphs (KG). A typical approach collects nodes relevant to the QA pair from a KG to form a Working Graph (WG) followed by reasoning using Graph Neural Networks(GNNs). This faces two major challenges: (i) it is difficult to capture all the information from the QA in the WG, and (ii) the WG contains some irrelevant nodes from the KG. To address these, we propose GrapeQA with two simple improvements on the WG: (i) Prominent Entities for Graph Augmentation identifies relevant text chunks from the QA pair and augments the WG with corresponding latent representations from the LM, and (ii) Context-Aware Node Pruning removes nodes that are less relevant to the QA pair. We evaluate our results on OpenBookQA, CommonsenseQA and MedQA-USMLE and see that GrapeQA shows consistent improvements over its LM + KG predecessor (QA-GNN in particular) and large improvements on OpenBookQA.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 22 of its 29 references that are in the map. First posted on arXiv 22 Mar 2023.

Builds on

22 of 29 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022GreaseLM: Graph REASoning Enhanced Language Models for Question Answering21 Jan

Other references · 21

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  3. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,790
  4. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,164
  5. 2019BioBERT: a pre-trained biomedical language representation model for biomedical text miningcited by 1,947
  6. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  7. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,356
  8. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,067
  9. 2020UnifiedQA: Crossing Format Boundaries With a Single QA Systemcited by 476
  10. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 388
  11. 2017A simple neural network module for relational reasoningcited by 346
  12. 2019FreeLB: Enhanced Adversarial Training for Natural Language Understandingcited by 264
9 more
  1. 2020Self-Alignment Pretraining for Biomedical Entity Representationscited by 237
  2. 2019KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoningcited by 216
  3. 2020Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answeringcited by 122
  4. 2019Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answeringcited by 68
  5. 2018Improving Natural Language Inference Using External Knowledge in the Science Questions Domaincited by 48
  6. 2020Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answeringcited by 44
  7. 2019Towards Generalizable Neuro-Symbolic Systems for Commonsense Question Answeringcited by 37
  8. 2019From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Projectcited by 33
  9. 2017Temporal Information Extraction for Question Answering Using Syntactic Dependencies in an LSTM-based Architecturecited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 8; 2025: 6; 2026: 1.

17 papers.

Sort:

By area:

  1. 2024Graph Retrieval-Augmented Generation: A Surveycited by 324
  2. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generationcited by 80
  3. 2025AgentRouter: A Knowledge-Graph-Guided LLM Router for Collaborative Multi-Agent Question Answeringcited by 32
  4. 2023KnowGPT: Knowledge Graph based Prompting for Large Language Modelscited by 31
  5. 2024Knowledge-Aware Query Expansion with Large Language Models for Textual and Relational Retrievalcited by 26
  6. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Surveycited by 18
  7. 2025Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Basescited by 11
  8. 2025NG-Router: Graph-Supervised Multi-Agent Collaboration for Nutrition Question Answeringcited by 10
  9. 2025How to Mitigate Information Loss in Knowledge Graphs for GraphRAG: Leveraging Triple Context Restoration and Query-Driven Feedbackcited by 6
  10. 2024How to Make LMs Strong Node Classifiers?cited by 4
  11. 2024Cost-efficient Knowledge-based Question Answering with Large Language Modelscited by 2
  12. 2024PipeNet: Question Answering with Semantic Pruning over Knowledge Graphscited by 1
5 more
  1. 2023How Can Context Help? Exploring Joint Retrieval of Passage and Personalized Contextcited by 0
  2. 2024Differentiating Choices via Commonality for Multiple-Choice Question Answeringcited by 0
  3. 2024Internal and External Knowledge Interactive Refinement Framework for Knowledge-Intensive Question Answeringcited by 0
  4. 2025KGFR: A Foundation Retriever for Generalized Knowledge Graph Question Answeringcited by 0
  5. 2026DA-RAG: Dynamic Attributed Community Search for Retrieval-Augmented Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Relation-Aware Language-Graph Transformer for Question Answering
  2. 2023Graph Reasoning for Question Answering with Triplet Retrieval
  3. 2024Integrating Large Language Models with Graph-based Reasoning for Conversational Question Answering
  4. 2026VisKG-LM: Compiling Knowledge Graphs into Visual Memory for Multiple-Choice Question Answering
  5. 2025PGDA-KGQA: A Prompt-Guided Generative Framework with Multiple Data Augmentation Strategies for Knowledge Graph Question Answering
  6. 2025Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering
  7. 2026Topology-Aware Reasoning over Incomplete Knowledge Graph with Graph-Based Soft Prompting
  8. 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering