Papers
arxiv:2512.00319

RL-Struct: A Lightweight Reinforcement Learning Framework for Reliable Structured Output in LLMs

Published on Nov 29, 2025
Authors:
,

Abstract

A reinforcement learning framework with a multi-dimensional reward function improves structured output accuracy in large language models by addressing the structure gap without significant computational overhead.

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language generation and reasoning. However, their integration into automated software ecosystems is often hindered by the "Structure Gap" - the inherent tension between the probabilistic nature of token generation and the deterministic requirements of structured data formats (e.g., JSON, XML). Traditional Supervised Fine-Tuning (SFT) often fails to enforce strict syntactic constraints, leading to "hallucinated" keys or malformed structures, while constrained decoding methods impose significant inference latency. In this paper, we propose a lightweight, efficient Reinforcement Learning (RL) framework to bridge this gap. We introduce a novel Multi-dimensional Reward Function that decomposes the structured output task into a hierarchy of constraints: structural integrity, format correctness, content accuracy, and validity. Leveraging Gradient Regularized Policy Optimization (GRPO), we enable the model to internalize these constraints without the need for a separate critic network, reducing peak VRAM usage by 40% compared to PPO. We validate our approach on multiple tasks, including complex recipe generation and structured math reasoning (GSM8K-JSON). Experimental results demonstrate that our method achieves 89.7% structural accuracy and 92.1% JSON validity, significantly outperforming both zero-shot baselines (e.g., GPT-3.5) and SFT on larger models like LLaMA-3-8B. Furthermore, we provide a detailed analysis of training dynamics, revealing a distinct self-paced curriculum where the model sequentially acquires syntactic proficiency before semantic accuracy. Our model is publicly available at https://huggingface.co/Freakz3z/Qwen-JSON.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2512.00319
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 1

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2512.00319 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2512.00319 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.