# RuleR: Improving LLM Controllability by Rule-based Data Recycling

arXiv: https://arxiv.org/abs/2406.15938 · HTML: https://mlsanity.com/paper/2406.15938/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 45 references that are in the map.
- First posted on arXiv 22 Jun 2024.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [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)
- [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)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [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)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning](https://mlsanity.com/paper/2312.15685/) (2023)
- [From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning](https://mlsanity.com/paper/2308.12032/) (2023)
- [TrustLLM: Trustworthiness in Large Language Models](https://mlsanity.com/paper/2401.05561/) (2024)
- [Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning](https://mlsanity.com/paper/2402.00530/) (2024)
- [Look at the First Sentence: Position Bias in Question Answering](https://mlsanity.com/paper/2004.14602/) (2020)
- [FOFO: A Benchmark to Evaluate LLMs' Format-Following Capability](https://mlsanity.com/paper/2402.18667/) (2024)
- [Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning](https://mlsanity.com/paper/2402.10110/) (2024)
- [Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks](https://mlsanity.com/paper/2310.13800/) (2023)
- [AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning](https://mlsanity.com/paper/2402.15506/) (2024)
- ["We Need Structured Output": Towards User-centered Constraints on Large Language Model Output](https://mlsanity.com/paper/2404.07362/) (2024)
- [Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents](https://mlsanity.com/paper/2402.00798/) (2024)
- [Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements](https://mlsanity.com/paper/2402.10614/) (2024)
- [Benchmarking Large Language Models on Controllable Generation under Diversified Instructions](https://mlsanity.com/paper/2401.00690/) (2024)
- [LFTK: Handcrafted Features in Computational Linguistics](https://mlsanity.com/paper/2305.15878/) (2023)

## Built on by (most cited first, 11 of 11)

- [The Perfect Blend: Redefining RLHF with Mixture of Judges](https://mlsanity.com/paper/2409.20370/) (2024)
- [WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents](https://mlsanity.com/paper/2410.07484/) (2024)
- [Towards Visual Text Grounding of Multimodal Large Language Model](https://mlsanity.com/paper/2504.04974/) (2025)
- [Divide-Verify-Refine: Can LLMs Self-Align with Complex Instructions?](https://mlsanity.com/paper/2410.12207/) (2024)
- [How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients](https://mlsanity.com/paper/2504.10766/) (2025)
- [What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding](https://mlsanity.com/paper/2506.06998/) (2025)
- [CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoning](https://mlsanity.com/paper/2507.00045/) (2025)
- [IF-CRITIC: Towards a Fine-Grained LLM Critic for Instruction-Following Evaluation](https://mlsanity.com/paper/2511.01014/) (2025)
- [From Image Generation to Infrastructure Design: a Multi-agent Pipeline for Street Design Generation](https://mlsanity.com/paper/2509.05469/) (2025)
- [An Efficient Hybrid Sparse Attention with CPU-GPU Parallelism for Long-Context Inference](https://mlsanity.com/paper/2605.07719/) (2026)
- [Enhancing Complex Instruction Following for Large Language Models with Mixture-of-Contexts Fine-tuning](https://mlsanity.com/paper/2505.11922/) (2025)

## Abstract (arXiv)

Large language models (LLMs) still lack delicate controllability over their responses, which is critical to enhancing their performance and the user experience. However, curating supervised fine-tuning (SFT) datasets to improve LLM controllability usually relies on human experts or proprietary LLMs, which requires additional costs. To bridge this gap, we propose Rule-based Data Recycling (RuleR), a data augmentation method incorporating multiple constraints into the original data samples according to predefined rules, which creates new training tasks to consolidate the controllability of LLMs. Instead of creating new data from scratch, RuleR "recycles" existing data by simply applying rule-based edits to their responses and appending the rule-instructions in their original instructions. Experimental results demonstrate RuleR's effectiveness in improving LLM controllability while maintaining general instruction-following capabilities.