mlsanityData to 7 Oct 2026

Self-training Large Language Models through Knowledge Detection

arXiv 2406.11275 ↗First posted 17 Jun 2024cs.CLcited by 8

On the map: Synthetic data and self-improvement for LLMs → Synthetic reasoning data and bootstrapping

Abstract (arXiv)

Large language models (LLMs) often necessitate extensive labeled datasets and training compute to achieve impressive performance across downstream tasks. This paper explores a self-training paradigm, where the LLM autonomously curates its own labels and selectively trains on unknown data samples identified through a reference-free consistency method. Empirical evaluations demonstrate significant improvements in reducing hallucination in generation across multiple subjects. Furthermore, the selective training framework mitigates catastrophic forgetting in out-of-distribution benchmarks, addressing a critical limitation in training LLMs. Our findings suggest that such an approach can substantially reduce the dependency on large labeled datasets, paving the way for more scalable and cost-effective language model training.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Placed in Synthetic reasoning data and bootstrapping, one of 13 directions in Synthetic data and self-improvement for LLMs. Builds on 24 of its 37 references that are in the map. First posted on arXiv 17 Jun 2024.

Builds on

24 of 37 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Large Language Models Can Self-Improve20 Oct

Other references · 23

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  4. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  5. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
  6. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  7. 2019Language Models as Knowledge Bases?cited by 1,922
  8. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,259
  9. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,219
  10. 2023An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuningcited by 622
  11. 2024TinyLlama: An Open-Source Small Language Modelcited by 604
  12. 2023FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarioscited by 247
11 more
  1. 2024Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positivecited by 239
  2. 2023Fine-tuning Language Models for Factualitycited by 219
  3. 2022Generating Training Data with Language Models: Towards Zero-Shot Language Understandingcited by 199
  4. 2021Towards Continual Knowledge Learning of Language Modelscited by 172
  5. 2019Revisiting Self-Training for Neural Sequence Generationcited by 154
  6. 2023Inspecting and Editing Knowledge Representations in Language Modelscited by 140
  7. 2022Explanations from Large Language Models Make Small Reasoners Bettercited by 123
  8. 2023Post Hoc Explanations of Language Models Can Improve Language Modelscited by 50
  9. 2024Learning to Trust Your Feelings: Leveraging Self-awareness in LLMs for Hallucination Mitigationcited by 43
  10. 2023Assessing the Reliability of Large Language Model Knowledgecited by 13
  11. 2024Plausible Extractive Rationalization through Semi-Supervised Entailment Signalcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 3; 2026: 1.

8 papers.

  1. 2025SEA-HELM: Southeast Asian Holistic Evaluation of Language Modelscited by 17
  2. 2025SEA-LION: Southeast Asian Languages in One Networkcited by 17
  3. 2024Towards Faithful Natural Language Explanations: A Study Using Activation Patching in Large Language Modelscited by 14
  4. 2024VideoSAVi: Self-Aligned Video Language Models without Human Supervisioncited by 7
  5. 2024SusGen-GPT: A Data-Centric LLM for Financial NLP and Sustainability Report Generationcited by 7
  6. 2025GRAM-R2: Self-Training Generative Foundation Reward Models for Reward Reasoningcited by 7
  7. 2026MeMo: Memory as a Modelcited by 4
  8. 2024Negation Blindness in Large Language Models: Unveiling the NO Syndrome in Image Generationcited by 3

Similar, not cited

Close in wording, no citation either way

  1. 2024Preserving Knowledge in Large Language Model with Model-Agnostic Self-Decompression
  2. 2026PRISM: A Unified Framework for Post-Training LLMs Without Verifiable Rewards
  3. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies
  4. 2023Large Language Models Suffer From Their Own Output: An Analysis of the Self-Consuming Training Loop
  5. 2024Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach
  6. 2025Self-Training Large Language Models for Tool-Use Without Demonstrations
  7. 2026Self-Improvement of Large Language Models: A Technical Overview and Future Outlook
  8. 2026OPSDL: On-Policy Self-Distillation for Long-Context Language Models