mlsanityData to 7 Oct 2026

Reinforcement learning to improve large language model-based automated code compliance systems

arXiv 2606.22402 ↗First posted 21 Jun 2026cs.SE cs.AI cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Large language model (LLM)-based approaches for automated code compliance (ACC) of building regulations are prone to generating incorrect and hallucinated computer-processable rules. This paper introduces P4IR, a two-stage framework that uses supervised fine-tuning (SFT) to instill domain knowledge in an LLM, followed by Group Relative Policy Optimization (GRPO) to improve the accuracy of the generated intermediate representations in the form of high-level code skeletons. The framework achieved reductions of up to 23.8% and 38.6% in tree edit distance and token-level Levenshtein distance respectively, relative to the SFT baselines. Comparative analysis demonstrates that this approach in a zero-shot setting outperforms leading LLMs in both code structure and semantics, specifically Claude Opus and Sonnet 4.5, GPT-5.2, Qwen-3-Max, and GLM-4.7, evaluated via few-shot prompting. Additionally, the GRPO stage produced a small yet statistically significant reduction in false positives. By combining SFT with GRPO to optimize directly for domain-specific objectives, this approach offers a path toward more accurate and reliable LLM-based ACC systems.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 45 references that are in the map. First posted on arXiv 21 Jun 2026.

Builds on

16 of 45 references.

References · 16

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  4. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  5. 2023Fine-tuning Language Models for Factualitycited by 219
  6. 2024Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputscited by 148
  7. 2025Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Modelscited by 144
  8. 2023Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedbackcited by 71
  9. 2023Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensemblescited by 55
  10. 2025Inverse Scaling in Test-Time Computecited by 49
  11. 2024Using Large Language Models for the Interpretation of Building Regulationscited by 6
  12. 2023Translating Regulatory Clauses into Executable Codes for Building Design Checking via Large Language Model Driven Function Matching and Composingcited by 5
4 more
  1. 2023A Text Classification-Based Approach for Evaluating and Enhancing the Machine Interpretability of Building Codescited by 4
  2. 2025LLM-assisted Graph-RAG Information Extraction from IFC Datacited by 3
  3. 2024Optimizing Performance: How Compact Models Match or Exceed GPT's Classification Capabilities through Fine-Tuningcited by 2
  4. 2026LLM attribution analysis across different fine-tuning strategies and model scales for automated code compliancecited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025From Reasoning to Code: GRPO Optimization for Underrepresented Languages
  2. 2025Improving LLM Reasoning for Vulnerability Detection via Group Relative Policy Optimization
  3. 2025Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them
  4. 2026GRPO Training Dynamics for Small Language Models
  5. 2025R1-Code-Interpreter: LLMs Reason with Code via Supervised and Multi-stage Reinforcement Learning
  6. 2026Soft Sequence Policy Optimization
  7. 2025RL-finetuning LLMs from on- and off-policy data with a single algorithm
  8. 2025Training-Free Group Relative Policy Optimization