# From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models

arXiv: https://arxiv.org/abs/2404.15846 · HTML: https://mlsanity.com/paper/2404.15846/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 57 references that are in the map.
- First posted on arXiv 24 Apr 2024.

## Builds on (most cited first, 30 of 40)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (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)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [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)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [WizardCoder: Empowering Code Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2306.08568/) (2023)
- [OpenAssistant Conversations -- Democratizing Large Language Model Alignment](https://mlsanity.com/paper/2304.07327/) (2023)
- [WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct](https://mlsanity.com/paper/2308.09583/) (2023)
- [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://mlsanity.com/paper/2401.08417/) (2024)
- [AgentTuning: Enabling Generalized Agent Abilities for LLMs](https://mlsanity.com/paper/2310.12823/) (2023)
- [Evaluating Large Language Models at Evaluating Instruction Following](https://mlsanity.com/paper/2310.07641/) (2023)
- [Teaching Small Language Models to Reason](https://mlsanity.com/paper/2212.08410/) (2022)
- [OpenChat: Advancing Open-source Language Models with Mixed-Quality Data](https://mlsanity.com/paper/2309.11235/) (2023)
- [Specializing Smaller Language Models towards Multi-Step Reasoning](https://mlsanity.com/paper/2301.12726/) (2023)
- [Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks](https://mlsanity.com/paper/2307.02477/) (2023)
- [Orca 2: Teaching Small Language Models How to Reason](https://mlsanity.com/paper/2311.11045/) (2023)
- [Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs](https://mlsanity.com/paper/2311.02262/) (2023)
- [Controlled Text Generation with Natural Language Instructions](https://mlsanity.com/paper/2304.14293/) (2023)
- [Continual Learning of Natural Language Processing Tasks: A Survey](https://mlsanity.com/paper/2211.12701/) (2022)

## Built on by (most cited first, 27 of 27)

- [LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs](https://mlsanity.com/paper/2408.07055/) (2024)
- [Checklists Are Better Than Reward Models For Aligning Language Models](https://mlsanity.com/paper/2507.18624/) (2025)
- [When Thinking Fails: The Pitfalls of Reasoning for Instruction-Following in LLMs](https://mlsanity.com/paper/2505.11423/) (2025)
- [MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents](https://mlsanity.com/paper/2510.15994/) (2025)
- [Do LLMs "know" internally when they follow instructions?](https://mlsanity.com/paper/2410.14516/) (2024)
- [Do LLMs estimate uncertainty well in instruction-following?](https://mlsanity.com/paper/2410.14582/) (2024)
- [Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models](https://mlsanity.com/paper/2506.01413/) (2025)
- [From Drafts to Answers: Unlocking LLM Potential via Aggregation Fine-Tuning](https://mlsanity.com/paper/2501.11877/) (2025)
- [RECAST: Expanding the Boundaries of LLMs' Complex Instruction Following with Multi-Constraint Data](https://mlsanity.com/paper/2505.19030/) (2025)
- [United Minds or Isolated Agents? Exploring Coordination of LLMs under Cognitive Load Theory](https://mlsanity.com/paper/2506.06843/) (2025)
- [A Course Correction in Steerability Evaluation: Revealing Miscalibration and Side Effects in LLMs](https://mlsanity.com/paper/2505.23816/) (2025)
- [Baichuan Alignment Technical Report](https://mlsanity.com/paper/2410.14940/) (2024)
- [When Is Enough Not Enough? Illusory Completion in Search Agents](https://mlsanity.com/paper/2602.07549/) (2026)
- [Semantic Probabilistic Control of Language Models](https://mlsanity.com/paper/2505.01954/) (2025)
- [PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimization](https://mlsanity.com/paper/2507.16679/) (2025)
- [Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models' Instruction Following](https://mlsanity.com/paper/2508.02150/) (2025)
- [Large-Scale Constraint Generation -- Can LLMs Parse Hundreds of Constraints?](https://mlsanity.com/paper/2509.24090/) (2025)
- [KCIF: Knowledge-Conditioned Instruction Following](https://mlsanity.com/paper/2410.12972/) (2024)
- [RefuteBench 2.0 -- Agentic Benchmark for Dynamic Evaluation of LLM Responses to Refutation Instruction](https://mlsanity.com/paper/2502.18308/) (2025)
- [Training with Pseudo-Code for Instruction Following](https://mlsanity.com/paper/2505.18011/) (2025)
- [One Token Away from Collapse: The Fragility of Instruction-Tuned Helpfulness](https://mlsanity.com/paper/2604.13006/) (2026)
- [SEIF: Self-Evolving Reinforcement Learning for Instruction Following](https://mlsanity.com/paper/2605.07465/) (2026)
- [Multi-Level Aware Preference Learning: Enhancing RLHF for Complex Multi-Instruction Tasks](https://mlsanity.com/paper/2505.12845/) (2025)
- [CodeAlignBench: Assessing Code Generation Models on Developer-Preferred Code Adjustments](https://mlsanity.com/paper/2510.27565/) (2025)
- [Cross-Relational Preference Learning for Better LLM Instruction Following](https://mlsanity.com/paper/2608.29352/) (2026)
- [ScopeIF: Improving Scope-Aware Precise Instruction-Following in Large Language Models via Graded Reward Modeling](https://mlsanity.com/paper/2609.32189/) (2026)
- [Learning to Prove, Not Just to Answer: Reinforcement Learning from Formal Verification for Natural-Language Logical Reasoning](https://mlsanity.com/paper/2609.37203/) (2026)

## Abstract (arXiv)

It is imperative for Large language models (LLMs) to follow instructions with elaborate requirements (i.e. Complex Instructions Following). Yet, it remains under-explored how to enhance the ability of LLMs to follow complex instructions with multiple constraints. To bridge the gap, we initially study what training data is effective in enhancing complex constraints following abilities. We found that training LLMs with instructions containing multiple constraints enhances their understanding of complex instructions, especially those with lower complexity levels. The improvement can even generalize to compositions of out-of-domain constraints. Additionally, we further propose methods addressing how to obtain and utilize the effective training data. Finally, we conduct extensive experiments to prove the effectiveness of our methods in terms of overall performance and training efficiency. We also demonstrate that our methods improve models' ability to follow instructions generally and generalize effectively across out-of-domain, in-domain, and adversarial settings, while maintaining general capabilities.