mlsanityData to 7 Oct 2026

Injecting New Knowledge into Large Language Models via Supervised Fine-Tuning

arXiv 2404.00213 ↗First posted 30 Mar 2024cs.CLcited by 56

Not on the map. Why?

Abstract (arXiv)

In recent years, Large Language Models (LLMs) have shown remarkable performance in generating human-like text, proving to be a valuable asset across various applications. However, adapting these models to incorporate new, out-of-domain knowledge remains a challenge, particularly for facts and events that occur after the model's knowledge cutoff date. This paper investigates the effectiveness of Supervised Fine-Tuning (SFT) as a method for knowledge injection in LLMs, specifically focusing on the domain of recent sporting events. We compare different dataset generation strategies -- token-based and fact-based scaling -- to create training data that helps the model learn new information. Our experiments on GPT-4 demonstrate that while token-based scaling can lead to improvements in Q&A accuracy, it may not provide uniform coverage of new knowledge. Fact-based scaling, on the other hand, offers a more systematic approach to ensure even coverage across all facts. We present a novel dataset generation process that leads to more effective knowledge ingestion through SFT, and our results show considerable performance improvements in Q&A tasks related to out-of-domain knowledge. This study contributes to the understanding of domain adaptation for LLMs and highlights the potential of SFT in enhancing the factuality of LLM responses in specific knowledge domains.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). Builds on 12 of its 17 references that are in the map. First posted on arXiv 30 Mar 2024.

Builds on

12 of 17 references.

References · 12

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  6. 2020K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapterscited by 318
  7. 2023Fine-tuning Language Models for Factualitycited by 219
  8. 2021KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extractioncited by 180
  9. 2020Common Sense or World Knowledge? Investigating Adapter-Based Knowledge Injection into Pretrained Transformerscited by 57
  10. 2020An Enhanced Knowledge Injection Model for Commonsense Generationcited by 21
  11. 2023KILM: Knowledge Injection into Encoder-Decoder Language Modelscited by 19
  12. 2016Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systemscited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 15; 2025: 25; 2026: 16.

56 papers.

Sort:

By area:

  1. 2026Self-Distillation Enables Continual Learningcited by 212
  2. 2025Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questionscited by 95
  3. 2024Synthetic continued pretrainingcited by 56
  4. 2024Knowledge Boundary of Large Language Models: A Surveycited by 36
  5. 2024On the Impact of Fine-Tuning on Chain-of-Thought Reasoningcited by 32
  6. 2024Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Passcited by 26
  7. 2024Adapting Multilingual LLMs to Low-Resource Languages using Continued Pre-training and Synthetic Corpuscited by 24
  8. 2024Efficient Knowledge Injection in LLMs via Self-Distillationcited by 22
  9. 2025How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Trainingcited by 22
  10. 2024On the Way to LLM Personalization: Learning to Remember User Conversationscited by 21
  11. 2024Perception of Knowledge Boundary for Large Language Models through Semi-open-ended Question Answeringcited by 20
  12. 2024Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teachingcited by 17
38 more
  1. 2025InfiniteICL: Breaking the Limit of Context Window Size via Long Short-term Memory Transformationcited by 16
  2. 2025Refining Input Guardrails: Enhancing LLM-as-a-Judge Efficiency Through Chain-of-Thought Fine-Tuning and Alignmentcited by 14
  3. 2025How new data permeates LLM knowledge and how to dilute itcited by 8
  4. 2025IDEAL: Data Equilibrium Adaptation for Multi-Capability Language Model Alignmentcited by 8
  5. 2026SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoningcited by 8
  6. 2024ChroKnowledge: Unveiling Chronological Knowledge of Language Models in Multiple Domainscited by 7
  7. 2025Bidirectional LMs are Better Knowledge Memorizers? A Benchmark for Real-world Knowledge Injectioncited by 7
  8. 2026Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Modelscited by 7
  9. 2024Structure-aware Domain Knowledge Injection for Large Language Modelscited by 6
  10. 2024Transfer Learning for Finetuning Large Language Modelscited by 5
  11. 2024Learning and Unlearning of Fabricated Knowledge in Language Modelscited by 4
  12. 2026JUDO: A Juxtaposed Domain-Oriented Multimodal Reasoner for Industrial Anomaly QAcited by 4
  13. 2024Synthetic Knowledge Ingestion: Towards Knowledge Refinement and Injection for Enhancing Large Language Modelscited by 3
  14. 2025Synthesize-on-Graph: Knowledgeable Synthetic Data Generation for Continue Pre-training of Large Language Modelscited by 3
  15. 2025Select to Know: An Internal-External Knowledge Self-Selection Framework for Domain-Specific Question Answeringcited by 3
  16. 2025Being Kind Isn't Always Being Safe: Diagnosing Affective Hallucination in LLMscited by 3
  17. 2025Towards EnergyGPT: A Large Language Model Specialized for the Energy Sectorcited by 3
  18. 2026MATRIX: A Multimodal Benchmark and Post-Training Framework for Materials Sciencecited by 3
  19. 2025Integrating Personality into Digital Humans: A Review of LLM-Driven Approaches for Virtual Realitycited by 2
  20. 2025Memorization and Knowledge Injection in Gated LLMscited by 2
  21. 2025Modelling and Classifying the Components of a Literature Reviewcited by 2
  22. 2025Comparing Knowledge Injection Methods for LLMs in a Low-Resource Regimecited by 2
  23. 2025Diffusion-Inspired Masked Fine-Tuning for Knowledge Injection in Autoregressive LLMscited by 2
  24. 2025LiveCLKTBench: Towards Reliable Evaluation of Cross-Lingual Knowledge Transfer in Multilingual LLMscited by 2
  25. 2026MixSD: Mixed Contextual Self-Distillation for Knowledge Injectioncited by 2
  26. 2025AC-LoRA: (Almost) Training-Free Access Control-Aware Multi-Modal LLMscited by 1
  27. 2025Data Doping or True Intelligence? Evaluating the Transferability of Injected Knowledge in LLMscited by 1
  28. 2025LMAR: Language Model Augmented Retriever for Domain-specific Knowledge Indexingcited by 1
  29. 2025SHERLOCK: Towards Dynamic Knowledge Adaptation in LLM-enhanced E-commerce Risk Managementcited by 1
  30. 2026Fine-Tuning Without Forgetting via Loss-Adaptive Learning Ratescited by 1
  31. 2024DELIA: Diversity-Enhanced Learning for Instruction Adaptation in Large Language Modelscited by 0
  32. 2025GeoGPT-RAG Technical Reportcited by 0
  33. 2025KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controlscited by 0
  34. 2025Yes-MT's Submission to the Low-Resource Indic Language Translation Shared Task in WMT 2024cited by 0
  35. 2025Enhancing Admission Inquiry Responses with Fine-Tuned Models and Retrieval-Augmented Generationcited by 0
  36. 2026Latent Knowledge as a Predictor of Fact Acquisition in Fine-Tuned Large Language Modelscited by 0
  37. 2026Continually self-improving AIcited by 0
  38. 2026SPA: A Simple but Tough-to-Beat Baseline for Knowledge Injectioncited by 0

50 most cited of 56 All 56 (JSON)