Complexity-aware fine-tuning
Not on the map. Why?
Abstract (arXiv)
General-purpose Large Language Models (LLMs) are frequently fine-tuned through supervised fine-tuning (SFT) to enhance performance in specific domains. Better results can be achieved by distilling the chain-of-thought of a larger model at the cost of numerous expensive calls and a much greater amount of data. We propose a novel blueprint for efficient fine-tuning that uses reasoning only for complex data identified by entropy. Specifically, across three small open models (≈ 3B) we split the training data into complexity categories by a single token answer entropy (ROC AUC 0.73), fine-tune large language models (LLMs) via SFT and distillation, and show that our pipeline significantly outperforms the standard SFT approach (0.58 vs 0.45 average accuracy) and outperforms the distillation approach (0.58 vs 0.56 average accuracy) while using 81% less data.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 19 of its 28 references that are in the map. First posted on arXiv 26 Jun 2025.
Builds on
19 of 28 references.
References · 19
- 2021Training Verifiers to Solve Math Word Problemscited by 10,109
- 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
- 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
- 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,919
- 2022Language Models (Mostly) Know What They Knowcited by 1,856
- 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,848
- 2023LIMA: Less Is More for Alignmentcited by 1,100
- 2024Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvementcited by 1,090
- 2023Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizescited by 737
- 2025Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAscited by 521
- 2023Symbolic Chain-of-Thought Distillation: Small Models Can Also "Think" Step-by-Stepcited by 148
7 more
- 2023LM-Polygraph: Uncertainty Estimation for Language Modelscited by 131
- 2024LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Datasetcited by 128
- 2024The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs: An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunitiescited by 64
- 2024SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Modelscited by 44
- 2024Towards Evaluating and Building Versatile Large Language Models for Medicinecited by 40
- 2024Strategic Data Ordering: Enhancing Large Language Model Performance through Curriculum Learningcited by 28
- 2025When an LLM is apprehensive about its answers -- and when its uncertainty is justifiedcited by 4
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2025Enhancing Large Language Model Reasoning via Selective Critical Token Fine-Tuning
- 2025Massive Supervised Fine-tuning Experiments Reveal How Data, Layer, and Training Factors Shape LLM Alignment Quality
- 2026InstructDiff: Domain-Adaptive Data Selection via Differential Entropy for Efficient LLM Fine-Tuning
- 2025Rethinking Supervised Fine-Tuning: Emphasizing Key Answer Tokens for Improved LLM Accuracy
- 2024Navigating the Landscape of Large Language Models: A Comprehensive Review and Analysis of Paradigms and Fine-Tuning Strategies
- 2026Diversity in Large Language Models under Supervised Fine-Tuning
- 2025Selective Self-to-Supervised Fine-Tuning for Generalization in Large Language Models
- 2024Scaling Sparse Fine-Tuning to Large Language Models