# Instruction Tuning with Human Curriculum

arXiv: https://arxiv.org/abs/2310.09518 · HTML: https://mlsanity.com/paper/2310.09518/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 93 references that are in the map.
- First posted on arXiv 14 Oct 2023.

## Builds on (most cited first, 30 of 37)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [The LAMBADA dataset: Word prediction requiring a broad discourse context](https://mlsanity.com/paper/1606.06031/) (2016)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning](https://mlsanity.com/paper/2308.08747/) (2023)
- [How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources](https://mlsanity.com/paper/2306.04751/) (2023)
- [Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor](https://mlsanity.com/paper/2212.09689/) (2022)
- [Orca: Progressive Learning from Complex Explanation Traces of GPT-4](https://mlsanity.com/paper/2306.02707/) (2023)
- [Pre-Trained Models: Past, Present and Future](https://mlsanity.com/paper/2106.07139/) (2021)
- [PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization](https://mlsanity.com/paper/2306.05087/) (2023)
- [Poisoning Language Models During Instruction Tuning](https://mlsanity.com/paper/2305.00944/) (2023)
- [Language models show human-like content effects on reasoning tasks](https://mlsanity.com/paper/2207.07051/) (2022)
- [When Do Curricula Work?](https://mlsanity.com/paper/2012.03107/) (2020)
- [Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum](https://mlsanity.com/paper/2308.14034/) (2023)
- [MM-LIMA: Less Is More for Alignment in Multi-Modal Datasets](https://mlsanity.com/paper/2308.12067/) (2023)

## Built on by (most cited first, 15 of 15)

- [Programming Refusal with Conditional Activation Steering](https://mlsanity.com/paper/2409.05907/) (2024)
- [The Best Instruction-Tuning Data are Those That Fit](https://mlsanity.com/paper/2502.04194/) (2025)
- [Prompt Curriculum Learning for Efficient LLM Post-Training](https://mlsanity.com/paper/2510.01135/) (2025)
- [Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models](https://mlsanity.com/paper/2412.02980/) (2024)
- [SPEED-RL: Faster Training of Reasoning Models via Online Curriculum Learning](https://mlsanity.com/paper/2506.09016/) (2025)
- [Problem-Solving Logic Guided Curriculum In-Context Learning for LLMs Complex Reasoning](https://mlsanity.com/paper/2502.15401/) (2025)
- [CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMs](https://mlsanity.com/paper/2602.03048/) (2026)
- [Self-Distilled Policy Gradient](https://mlsanity.com/paper/2606.04036/) (2026)
- [NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness](https://mlsanity.com/paper/2609.08183/) (2026)
- [ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning](https://mlsanity.com/paper/2510.18250/) (2025)
- [RefGlitch-Bench: A Benchmark for Reference-based Gameplay Glitch Detection with Vision-Language Models](https://mlsanity.com/paper/2604.11082/) (2026)
- [From Amateur to Master: Infusing Knowledge into LLMs via Automated Curriculum Learning](https://mlsanity.com/paper/2510.26336/) (2025)
- [Building an Ethical and Trustworthy Biomedical AI Ecosystem for the Translational and Clinical Integration of Foundational Models](https://mlsanity.com/paper/2408.01431/) (2024)
- [Empowering Large Language Models in Wireless Communication: A Novel Dataset and Fine-Tuning Framework](https://mlsanity.com/paper/2501.09631/) (2025)
- [OmniEdu: Open Foundation Models for Learning and Teaching](https://mlsanity.com/paper/2609.23088/) (2026)

## Abstract (arXiv)

In this work, we (1) introduce Curriculum Instruction Tuning, (2) explore the potential advantages of employing diverse curriculum strategies, and (3) delineate a synthetic instruction-response generation framework that complements our theoretical approach. Distinct from the existing instruction tuning dataset, our generation pipeline is systematically structured to emulate the sequential and orderly characteristic of human learning. Additionally, we describe a methodology for generating instruction-response datasets that extensively span the various stages of human education, from middle school through the graduate level, utilizing educational subject catalogs. Before training, we meticulously organize the instruction data to ensure that questions escalate in difficulty regarding (A) the subject matter and (B) the intricacy of the instructions. The findings of our study reveal that substantial improvements in performance can be achieved through the mere application of curriculum ordering to instruction data (achieving gains of +4.76 on TruthfulQA, +2.98 on MMLU, +2.8 on OpenbookQA, and +1.28 on ARC-hard) compared to random shuffling. This enhancement is achieved without incurring additional computational expenses. Through comprehensive experimentation, we observe that the advantages of our proposed method are consistently evident across nine benchmarks.