mlsanityData to 14 Oct 2026

Efficient Knowledge Infusion via KG-LLM Alignment

arXiv 2406.03746 ↗First posted 6 Jun 2024cs.CL cs.AIcited by 13

On the map: LLM alignment / RLHF / preference optimisation → LLM preference optimization methods

Abstract (arXiv)

To tackle the problem of domain-specific knowledge scarcity within large language models (LLMs), knowledge graph-retrievalaugmented method has been proven to be an effective and efficient technique for knowledge infusion. However, existing approaches face two primary challenges: knowledge mismatch between public available knowledge graphs and the specific domain of the task at hand, and poor information compliance of LLMs with knowledge graphs. In this paper, we leverage a small set of labeled samples and a large-scale corpus to efficiently construct domain-specific knowledge graphs by an LLM, addressing the issue of knowledge mismatch. Additionally, we propose a three-stage KG-LLM alignment strategyto enhance the LLM's capability to utilize information from knowledge graphs. We conduct experiments with a limited-sample setting on two biomedical question-answering datasets, and the results demonstrate that our approach outperforms existing baselines.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 22 of its 35 references that are in the map. First posted on arXiv 6 Jun 2024.

Builds on

22 of 35 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Training language models to follow instructions with human feedback4 Mar

Other references · 21

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  4. 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
  5. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  6. 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 843
  7. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 668
  8. 2019COMET: Commonsense Transformers for Automatic Knowledge Graph Constructioncited by 450
  9. 2021Symbolic Knowledge Distillation: from General Language Models to Commonsense Modelscited by 270
  10. 2023ChatDB: Augmenting LLMs with Databases as Their Symbolic Memorycited by 140
  11. 2019Span-based Joint Entity and Relation Extraction with Transformer Pre-trainingcited by 133
  12. 2023AlpaCare:Instruction-tuned Large Language Models for Medical Applicationcited by 90
9 more
  1. 2021JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphscited by 58
  2. 2023KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Basescited by 52
  3. 2023PiVe: Prompting with Iterative Verification Improving Graph-based Generative Capability of LLMscited by 44
  4. 2021Few-shot Knowledge Graph-to-Text Generation with Pretrained Language Modelscited by 29
  5. 2022BertNet: Harvesting Knowledge Graphs with Arbitrary Relations from Pretrained Language Modelscited by 20
  6. 2022GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text Generationcited by 16
  7. 2023FABULA: Intelligence Report Generation Using Retrieval-Augmented Narrative Constructioncited by 10
  8. 2020Chinese Medical Question Answer Matching Based on Interactive Sentence Representation Learningcited by 6
  9. 2023Commonsense Knowledge Graph Completion Via Contrastive Pretraining and Node Clusteringcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 7; 2026: 2.

13 papers.

Sort:

By area:

  1. 2024KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generationcited by 67
  2. 2024Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generationcited by 64
  3. 2024Retrieve, Summarize, Plan: Advancing Multi-hop Question Answering with an Iterative Approachcited by 40
  4. 2025KramaBench: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakescited by 33
  5. 2025STRUCTSENSE: A Task-Agnostic Agentic Framework for Structured Information Extraction with Human-In-The-Loop Evaluation and Benchmarkingcited by 8
  6. 2024Way to Specialist: Closing Loop Between Specialized LLM and Evolving Domain Knowledge Graphcited by 6
  7. 2025Aligning Knowledge Graphs and Language Models for Factual Accuracycited by 4
  8. 2025CliCARE: Grounding Large Language Models in Clinical Guidelines for Decision Support over Longitudinal Cancer Electronic Health Recordscited by 4
  9. 2025Large Language Models for Knowledge Graph Embedding: A Surveycited by 3
  10. 2025Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A Surveycited by 2
  11. 2026From Token to Token Pair: Efficient Prompt Compression for Large Language Models in Clinical Predictioncited by 2
  12. 2025Bi'an: A Bilingual Benchmark and Model for Hallucination Detection in Retrieval-Augmented Generationcited by 1
1 more
  1. 2026Structure-Internalized Rule Language Model for Faithful Knowledge Graph Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024GLaM: Fine-Tuning Large Language Models for Domain Knowledge Graph Alignment via Neighborhood Partitioning and Generative Subgraph Encoding
  2. 2025KG-LLM-Bench: A Scalable Benchmark for Evaluating LLM Reasoning on Textualized Knowledge Graphs
  3. 2025Fusing Knowledge and Language: A Comparative Study of Knowledge Graph-Based Question Answering with LLMs
  4. 2024Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation
  5. 2023Knowledge Solver: Teaching LLMs to Search for Domain Knowledge from Knowledge Graphs
  6. 2023LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities
  7. 2023KnowledgeNavigator: Leveraging Large Language Models for Enhanced Reasoning over Knowledge Graph
  8. 2026A Human-in-the-Loop, LLM-Centered Architecture for Knowledge-Graph Question Answering