mlsanityData to 7 Oct 2026

Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Survey

arXiv 2502.10708 ↗First posted 15 Feb 2025cs.CLcited by 47

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) have demonstrated remarkable success in various tasks such as natural language understanding, text summarization, and machine translation. However, their general-purpose nature often limits their effectiveness in domain-specific applications that require specialized knowledge, such as healthcare, chemistry, or legal analysis. To address this, researchers have explored diverse methods to enhance LLMs by integrating domain-specific knowledge. In this survey, we provide a comprehensive overview of these methods, which we categorize into four key approaches: dynamic knowledge injection, static knowledge embedding, modular adapters, and prompt optimization. Each approach offers unique mechanisms to equip LLMs with domain expertise, balancing trade-offs between flexibility, scalability, and efficiency. We discuss how these methods enable LLMs to tackle specialized tasks, compare their advantages and disadvantages, evaluate domain-specific LLMs against general LLMs, and highlight the challenges and opportunities in this emerging field. For those interested in delving deeper into this area, we also summarize the commonly used datasets and benchmarks. To keep researchers updated on the latest studies, we maintain an open-source at: https://github.com/abilliyb/Knowledge_Injection_Survey_Papers, dedicated to documenting research in the field of specialized LLM.

Key facts. Cited by 47 papers in the map (data through 7 Oct 2026). Builds on 53 of its 97 references that are in the map. First posted on arXiv 15 Feb 2025.

Builds on

53 of 97 references.

References · 53

  1. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  2. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  3. 2022Large Language Models Encode Clinical Knowledgecited by 1,807
  4. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,324
  5. 2019PubMedQA: A Dataset for Biomedical Research Question Answeringcited by 1,271
  6. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,259
  7. 2023BloombergGPT: A Large Language Model for Financecited by 923
  8. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
  9. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 437
  10. 2023Towards Expert-Level Medical Question Answering with Large Language Modelscited by 382
  11. 2020K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapterscited by 318
  12. 2013Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Textscited by 310
38 more
  1. 2024Knowledge Conflicts for LLMs: A Surveycited by 274
  2. 2023FinGPT: Open-Source Financial Large Language Modelscited by 244
  3. 2023PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Financecited by 217
  4. 2021On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptationcited by 147
  5. 2017PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstractscited by 123
  6. 2022WHEN FLUE MEETS FLANG: Benchmarks and Large Pre-trained Language Model for Financial Domaincited by 117
  7. 2023GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Informationcited by 115
  8. 2021Lifelong Pretraining: Continually Adapting Language Models to Emerging Corporacited by 114
  9. 2023SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversationscited by 109
  10. 2023Lift Yourself Up: Retrieval-augmented Text Generation with Self Memorycited by 103
  11. 2020CrossNER: Evaluating Cross-Domain Named Entity Recognitioncited by 102
  12. 2021PsyQA: A Chinese Dataset for Generating Long Counseling Text for Mental Health Supportcited by 92
  13. 2023XuanYuan 2.0: A Large Chinese Financial Chat Model with Hundreds of Billions Parameterscited by 92
  14. 2024BioMedLM: A 2.7B Parameter Language Model Trained On Biomedical Textcited by 85
  15. 2025MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilotcited by 83
  16. 2023EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Educationcited by 80
  17. 2023BBT-Fin: Comprehensive Construction of Chinese Financial Domain Pre-trained Language Model, Corpus and Benchmarkcited by 60
  18. 2023Instruct-FinGPT: Financial Sentiment Analysis by Instruction Tuning of General-Purpose Large Language Modelscited by 58
  19. 2024BioT5+: Towards Generalized Biological Understanding with IUPAC Integration and Multi-task Tuningcited by 54
  20. 2024From Skepticism to Acceptance: Simulating the Attitude Dynamics Toward Fake Newscited by 51
  21. 2024DALK: Dynamic Co-Augmentation of LLMs and KG to answer Alzheimer's Disease Questions with Scientific Literaturecited by 50
  22. 2023SMILE: Single-turn to Multi-turn Inclusive Language Expansion via ChatGPT for Mental Health Supportcited by 46
  23. 2023LLM-based Medical Assistant Personalization with Short- and Long-Term Memory Coordinationcited by 46
  24. 2025ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoningcited by 41
  25. 2024EmoLLM: Multimodal Emotional Understanding Meets Large Language Modelscited by 31
  26. 2024Decoding Echo Chambers: LLM-Powered Simulations Revealing Polarization in Social Networkscited by 31
  27. 2023KnowGPT: Knowledge Graph based Prompting for Large Language Modelscited by 30
  28. 2024BiomedRAG: A Retrieval Augmented Large Language Model for Biomedicinecited by 30
  29. 2024FinLlama: Financial Sentiment Classification for Algorithmic Trading Applicationscited by 22
  30. 2024Foundational Large Language Models for Materials Researchcited by 18
  31. 2022Meta-Learning the Difference: Preparing Large Language Models for Efficient Adaptationcited by 14
  32. 2023Social-LLM: Modeling User Behavior at Scale using Language Models and Social Network Datacited by 11
  33. 2024DARWIN 1.5: Large Language Models as Materials Science Adapted Learnerscited by 9
  34. 2025LLM Alignment as Retriever Optimization: An Information Retrieval Perspectivecited by 7
  35. 2024Structure-aware Domain Knowledge Injection for Large Language Modelscited by 6
  36. 2024ScholarChemQA: Unveiling the Power of Language Models in Chemical Research Question Answeringcited by 5
  37. 2023Biomedical Entity Linking with Triple-aware Pre-Trainingcited by 2
  38. 2024SA-MDKIF: A Scalable and Adaptable Medical Domain Knowledge Injection Framework for Large Language Modelscited by 2

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 32; 2026: 15.

47 papers.

Sort:

By area:

  1. 2025Large Language Models Meet Knowledge Graphs for Question Answering: Synthesis and Opportunitiescited by 30
  2. 2025AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunitiescited by 26
  3. 2025DyFlow: Dynamic Workflow Framework for Agentic Reasoningcited by 22
  4. 2025Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Modelscited by 15
  5. 2025Reasoning-Enhanced Domain-Adaptive Pretraining of Multimodal Large Language Models for Short Video Content Governancecited by 13
  6. 2025Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Fixingcited by 11
  7. 2025Mitigating the Safety Alignment Tax with Null-Space Constrained Policy Optimizationcited by 11
  8. 2025G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledgecited by 9
  9. 2025Beyond Survival: Evaluating LLMs in Social Deduction Games with Human-Aligned Strategiescited by 9
  10. 2025Bidirectional LMs are Better Knowledge Memorizers? A Benchmark for Real-world Knowledge Injectioncited by 7
  11. 2025Knowledge Augmented Complex Problem Solving with Large Language Models: A Surveycited by 6
  12. 2025CEQuest: Benchmarking Large Language Models for Construction Estimationcited by 6
35 more
  1. 2025Bridging Industrial Expertise and XR with LLM-Powered Conversational Agentscited by 4
  2. 2026JUDO: A Juxtaposed Domain-Oriented Multimodal Reasoner for Industrial Anomaly QAcited by 4
  3. 2025Generative AI Enhanced Financial Risk Management Information Retrievalcited by 3
  4. 2025Flipping Knowledge Distillation: Leveraging Small Models' Expertise to Enhance LLMs in Text Matchingcited by 3
  5. 2025SNaRe: Domain-aware Data Generation for Low-Resource Event Detectioncited by 2
  6. 2025Multimodal Policy Internalization for Conversational Agentscited by 2
  7. 2026EDCO: Dynamic Curriculum Orchestration for Domain-specific Large Language Model Fine-tuningcited by 2
  8. 2025AC-LoRA: (Almost) Training-Free Access Control-Aware Multi-Modal LLMscited by 1
  9. 2025Comparative Analysis of AI Agent Architectures for Entity Relationship Classificationcited by 1
  10. 2025RELRaE: LLM-Based Relationship Extraction, Labelling, Refinement, and Evaluationcited by 1
  11. 2025Gene-R1: Reasoning with Data-Augmented Lightweight LLMs for Gene Set Analysiscited by 1
  12. 2025KAHAN: Knowledge-Augmented Hierarchical Analysis and Narration for Financial Data Narrationcited by 1
  13. 2025Embedding Domain Knowledge for Large Language Models via Reinforcement Learning from Augmented Generationcited by 1
  14. 2025Analyzing and Internalizing Complex Policy Documents for LLM Agentscited by 1
  15. 2025EfficientXpert: Efficient Domain Adaptation for Large Language Models via Propagation-Aware Pruningcited by 1
  16. 2026Self Knowledge Re-expression: A Fully Local Method for Adapting LLMs to Tasks Using Intrinsic Knowledgecited by 1
  17. 2026TeleCom-Bench: How Far Are Large Language Models from Industrial Telecommunication Applications?cited by 1
  18. 2026One Model, Multiple Goals: Adaptive Multi-Objective Learning for E-commerce Dialogue Systemscited by 1
  19. 2026Measure, Don't Optimize: Forecasting Recovery in LLM Unlearningcited by 1
  20. 2025Keep the General, Inject the Specific: Structured Dialogue Fine-Tuning for Knowledge Injection without Catastrophic Forgettingcited by 0
  21. 2025SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decodingcited by 0
  22. 2025Collaborative Editable Modelcited by 0
  23. 2025Knowledge Conceptualization Impacts RAG Efficacycited by 0
  24. 2025KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controlscited by 0
  25. 2025Evontree: Ontology Rule-Guided Self-Evolution of Large Language Modelscited by 0
  26. 2025Modeling User-System Behavior for Training-free Building of Private Domain Conversational Agentscited by 0
  27. 2026A unified foundational framework for knowledge injection and evaluation of Large Language Models in Combustion Sciencecited by 0
  28. 2026GSI Agent: Domain Knowledge Enhancement for Large Language Models in Green Stormwater Infrastructurecited by 0
  29. 2026LegalMidm: Use-Case-Driven Legal Domain Specialization for Korean Large Language Modelcited by 0
  30. 2026Decoupled Mixture-of-Experts for Parametric Knowledge Injectioncited by 0
  31. 2026Global Logic and Local Search: Dual-Stream Multimodal In-Context Learning for Verifiable Industrial Anomaly Detectioncited by 0
  32. 2026AdaptAgent: A Multi-agent, Domain-Guided Reasoning Framework for Code Adaptationcited by 0
  33. 2026Data Scout: Targeted Web Crawling for Domain-Specific Pretraining Corporacited by 0
  34. 2026Cognition on Graph: Navigating Massive Knowledge Space via Cognitive Cycles and Bidirectional Graph-Text Synergycited by 0
  35. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoningcited by 0