mlsanityData to 14 Oct 2026

Teaching According to Talents! Instruction Tuning LLMs with Competence-Aware Curriculum Learning

arXiv 2509.13790 ↗First posted 17 Sep 2025cs.CL cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

Efficient instruction tuning aims to enhance the ultimate performance of large language models (LLMs) trained on a given instruction dataset. Curriculum learning as a typical data organization strategy has shown preliminary effectiveness in instruction tuning. However, current curriculum tuning methods suffer from the curriculum rigidity, since they rely solely on static heuristic difficulty metrics. These methods fail to adapt to the evolving capabilities of models during training, resulting in a fixed and potentially sub-optimal learning trajectory. To address the issue, Competence-Aware Multi-Perspective cUrriculum inStruction tuning framework termed CAMPUS is proposed. CAMPUS offers several advantages: (1) Dynamic selection for sub-curriculum. (2) Competency-aware adjustment to the curriculum schedule. (3) Multiple difficulty-based scheduling. Extensive experiments prove the superior performance of CAMPUS, compared to other state-of-the-art baselines for efficient instruction tuning.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 45 of its 61 references that are in the map. First posted on arXiv 17 Sep 2025.

Builds on

45 of 61 references.

References · 45

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  5. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  6. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  7. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  8. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  9. 2021Program Synthesis with Large Language Modelscited by 3,637
  10. 2023Qwen Technical Reportcited by 3,344
  11. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  12. 2023LIMA: Less Is More for Alignmentcited by 1,100
33 more
  1. 2023What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuningcited by 364
  2. 2023From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuningcited by 307
  3. 2022Binding Language Models in Symbolic Languagescited by 228
  4. 2023How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Compositioncited by 223
  5. 2023#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Modelscited by 109
  6. 2024Large Language Models Meet NLP: A Surveycited by 103
  7. 2024A Survey on Data Selection for LLM Instruction Tuningcited by 77
  8. 2024Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Surveycited by 76
  9. 2024Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agentcited by 65
  10. 2021Are we ready for a new paradigm shift? A Survey on Visual Deep MLPcited by 63
  11. 2024LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewingcited by 62
  12. 2022The Past Mistake is the Future Wisdom: Error-driven Contrastive Probability Optimization for Chinese Spell Checkingcited by 56
  13. 2023On the (In)Effectiveness of Large Language Models for Chinese Text Correctioncited by 54
  14. 2023Self-Evolved Diverse Data Sampling for Efficient Instruction Tuningcited by 52
  15. 2023LatEval: An Interactive LLMs Evaluation Benchmark with Incomplete Information from Lateral Thinking Puzzlescited by 41
  16. 2023A Preliminary Study of the Intrinsic Relationship between Complexity and Alignmentcited by 33
  17. 2022Learning from the Dictionary: Heterogeneous Knowledge Guided Fine-tuning for Chinese Spell Checkingcited by 31
  18. 2022Contrastive Learning with Hard Negative Entities for Entity Set Expansioncited by 26
  19. 2022Linguistic Rules-Based Corpus Generation for Native Chinese Grammatical Error Correctioncited by 25
  20. 2024Let LLMs Take on the Latest Challenges! A Chinese Dynamic Question Answering Benchmarkcited by 22
  21. 2025DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokenscited by 22
  22. 2023Vision, Deduction and Alignment: An Empirical Study on Multi-modal Knowledge Graph Alignmentcited by 19
  23. 2023SeqGPT: An Out-of-the-box Large Language Model for Open Domain Sequence Understandingcited by 18
  24. 2025Refine Knowledge of Large Language Models via Adaptive Contrastive Learningcited by 15
  25. 2022Contextual Similarity is More Valuable than Character Similarity: An Empirical Study for Chinese Spell Checkingcited by 14
  26. 2025One Example Shown, Many Concepts Known! Counterexample-Driven Conceptual Reasoning in Mathematical LLMscited by 14
  27. 2023Correct Like Humans: Progressive Learning Framework for Chinese Text Error Correctioncited by 13
  28. 2023MESED: A Multi-modal Entity Set Expansion Dataset with Fine-grained Semantic Classes and Hard Negative Entitiescited by 13
  29. 2024Mitigating Catastrophic Forgetting in Multi-domain Chinese Spelling Correction by Multi-stage Knowledge Transfer Frameworkcited by 4
  30. 2024Exploring the Implicit Semantic Ability of Multimodal Large Language Models: A Pilot Study on Entity Set Expansioncited by 3
  31. 2024Loss-Aware Curriculum Learning for Chinese Grammatical Error Correctioncited by 3
  32. 2025MDIT: A Model-free Data Interpolation Method for Diverse Instruction Tuningcited by 3
  33. 2022A Curriculum Learning Approach for Multi-domain Text Classification Using Keyword weight Rankingcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026LiFT: How to Enable In-Context Learning for Longitudinal Modellingcited by 0
  2. 2026Curriculum Learning for Safety Alignmentcited by 0