mlsanityData to 7 Oct 2026

RuleR: Improving LLM Controllability by Rule-based Data Recycling

arXiv 2406.15938 ↗First posted 22 Jun 2024cs.CL cs.AI cs.LGcited by 11

Not on the map. Why?

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.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 30 of its 45 references that are in the map. First posted on arXiv 22 Jun 2024.

Builds on

30 of 45 references.

References · 30

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  5. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  6. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  7. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  8. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,018
  9. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  10. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  11. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  12. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
18 more
  1. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,116
  2. 2023LIMA: Less Is More for Alignmentcited by 1,080
  3. 2023Large Language Models are not Fair Evaluatorscited by 1,050
  4. 2022Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Taskscited by 858
  5. 2023What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuningcited by 354
  6. 2023From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuningcited by 301
  7. 2024TrustLLM: Trustworthiness in Large Language Modelscited by 280
  8. 2024Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuningcited by 134
  9. 2020Look at the First Sentence: Position Bias in Question Answeringcited by 83
  10. 2024FOFO: A Benchmark to Evaluate LLMs' Format-Following Capabilitycited by 79
  11. 2024Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuningcited by 57
  12. 2023Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Taskscited by 53
  13. 2024AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learningcited by 53
  14. 2024"We Need Structured Output": Towards User-centered Constraints on Large Language Model Outputcited by 46
  15. 2024Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agentscited by 39
  16. 2024Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statementscited by 33
  17. 2024Benchmarking Large Language Models on Controllable Generation under Diversified Instructionscited by 26
  18. 2023LFTK: Handcrafted Features in Computational Linguisticscited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 7; 2026: 1.

11 papers.

  1. 2024The Perfect Blend: Redefining RLHF with Mixture of Judgescited by 43
  2. 2024WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agentscited by 24
  3. 2025Towards Visual Text Grounding of Multimodal Large Language Modelcited by 18
  4. 2025How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradientscited by 8
  5. 2024Divide-Verify-Refine: Can LLMs Self-Align with Complex Instructions?cited by 7
  6. 2025What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decodingcited by 7
  7. 2025CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoningcited by 4
  8. 2025IF-CRITIC: Towards a Fine-Grained LLM Critic for Instruction-Following Evaluationcited by 4
  9. 2025From Image Generation to Infrastructure Design: a Multi-agent Pipeline for Street Design Generationcited by 3
  10. 2026An Efficient Hybrid Sparse Attention with CPU-GPU Parallelism for Long-Context Inferencecited by 3
  11. 2025Enhancing Complex Instruction Following for Large Language Models with Mixture-of-Contexts Fine-tuningcited by 2