# Chain-of-Instructions: Compositional Instruction Tuning on Large Language Models

arXiv: https://arxiv.org/abs/2402.11532 · HTML: https://mlsanity.com/paper/2402.11532/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 38 references that are in the map.
- First posted on arXiv 18 Feb 2024.

## Builds on (most cited first, 27 of 27)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes](https://mlsanity.com/paper/2305.02301/) (2023)
- [Cross-Task Generalization via Natural Language Crowdsourcing Instructions](https://mlsanity.com/paper/2104.08773/) (2021)
- [Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor](https://mlsanity.com/paper/2212.09689/) (2022)
- [Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought](https://mlsanity.com/paper/2210.01240/) (2022)
- [Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision](https://mlsanity.com/paper/2305.03047/) (2023)
- [Measuring Compositional Generalization: A Comprehensive Method on Realistic Data](https://mlsanity.com/paper/1912.09713/) (2019)
- [Symbolic Knowledge Distillation: from General Language Models to Commonsense Models](https://mlsanity.com/paper/2110.07178/) (2021)
- [COGS: A Compositional Generalization Challenge Based on Semantic Interpretation](https://mlsanity.com/paper/2010.05465/) (2020)
- [Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias](https://mlsanity.com/paper/2306.15895/) (2023)
- [Generating Datasets with Pretrained Language Models](https://mlsanity.com/paper/2104.07540/) (2021)
- [WikiLingua: A New Benchmark Dataset for Cross-Lingual Abstractive Summarization](https://mlsanity.com/paper/2010.03093/) (2020)
- [The Turking Test: Can Language Models Understand Instructions?](https://mlsanity.com/paper/2010.11982/) (2020)
- [Learning from Task Descriptions](https://mlsanity.com/paper/2011.08115/) (2020)
- [CoEdIT: Text Editing by Task-Specific Instruction Tuning](https://mlsanity.com/paper/2305.09857/) (2023)
- [Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learning](https://mlsanity.com/paper/2306.01150/) (2023)
- [CESAR: Automatic Induction of Compositional Instructions for Multi-turn Dialogs](https://mlsanity.com/paper/2311.17376/) (2023)

## Built on by (most cited first, 9 of 9)

- [APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay](https://mlsanity.com/paper/2504.03601/) (2025)
- [Benchmarking Complex Instruction-Following with Multiple Constraints Composition](https://mlsanity.com/paper/2407.03978/) (2024)
- [Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective](https://mlsanity.com/paper/2412.14135/) (2024)
- [Facilitating Multi-turn Function Calling for LLMs via Compositional Instruction Tuning](https://mlsanity.com/paper/2410.12952/) (2024)
- [Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models](https://mlsanity.com/paper/2505.14810/) (2025)
- [Fine-tuning Large Language Models with Sequential Instructions](https://mlsanity.com/paper/2403.07794/) (2024)
- [Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models](https://mlsanity.com/paper/2506.01413/) (2025)
- [Training with Pseudo-Code for Instruction Following](https://mlsanity.com/paper/2505.18011/) (2025)
- [UniTransfer: Video Concept Transfer via Progressive Spatial and Timestep Decomposition](https://mlsanity.com/paper/2509.21086/) (2025)

## Abstract (arXiv)

Fine-tuning large language models (LLMs) with a collection of large and diverse instructions has improved the model's generalization to different tasks, even for unseen tasks. However, most existing instruction datasets include only single instructions, and they struggle to follow complex instructions composed of multiple subtasks. In this work, we propose a novel concept of compositional instructions called chain-of-instructions (CoI), where the output of one instruction becomes an input for the next like a chain. Unlike the conventional practice of solving single instruction tasks, our proposed method encourages a model to solve each subtask step by step until the final answer is reached. CoI-tuning (i.e., fine-tuning with CoI instructions) improves the model's ability to handle instructions composed of multiple subtasks as well as unseen composite tasks such as multilingual summarization. Overall, our study find that simple CoI tuning of existing instruction data can provide consistent generalization to solve more complex, unseen, and longer chains of instructions.