# FMBench: Adaptive Large Language Model Output Formatting

arXiv: https://arxiv.org/abs/2602.06384 · HTML: https://mlsanity.com/paper/2602.06384/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 24 references that are in the map.
- First posted on arXiv 6 Feb 2026.

## Builds on (most cited first, 21 of 21)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction](https://mlsanity.com/paper/2304.08085/) (2023)
- [GPT-NER: Named Entity Recognition via Large Language Models](https://mlsanity.com/paper/2304.10428/) (2023)
- [Does Prompt Formatting Have Any Impact on LLM Performance?](https://mlsanity.com/paper/2411.10541/) (2024)
- [Checklists Are Better Than Reward Models For Aligning Language Models](https://mlsanity.com/paper/2507.18624/) (2025)
- [Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation](https://mlsanity.com/paper/2403.06988/) (2024)
- [Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models](https://mlsanity.com/paper/2408.02442/) (2024)
- [XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models](https://mlsanity.com/paper/2411.15100/) (2024)
- [Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition](https://mlsanity.com/paper/2505.22375/) (2025)
- [AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following](https://mlsanity.com/paper/2511.10507/) (2025)
- [VerIF: Verification Engineering for Reinforcement Learning in Instruction Following](https://mlsanity.com/paper/2506.09942/) (2025)
- [StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs](https://mlsanity.com/paper/2505.20139/) (2025)
- [From Prompts to Templates: A Systematic Prompt Template Analysis for Real-world LLMapps](https://mlsanity.com/paper/2504.02052/) (2025)
- [SLOT: Structuring the Output of Large Language Models](https://mlsanity.com/paper/2505.04016/) (2025)
- [Beyond Prompt Content: Enhancing LLM Performance via Content-Format Integrated Prompt Optimization](https://mlsanity.com/paper/2502.04295/) (2025)
- [MulDimIF: A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language Models](https://mlsanity.com/paper/2505.07591/) (2025)
- [ReFF: Reinforcing Format Faithfulness in Language Models across Varied Tasks](https://mlsanity.com/paper/2412.09173/) (2024)
- [Replay Failures as Successes: Sample-Efficient Reinforcement Learning for Instruction Following](https://mlsanity.com/paper/2512.23457/) (2025)

## Built on by (most cited first, 1 of 1)

- [LatentMD: Benchmarking Markdown Boundary Failures in LLM-Generated Text](https://mlsanity.com/paper/2609.06993/) (2026)

## Abstract (arXiv)

Producing outputs that satisfy both semantic intent and format constraints is essential for deploying large language models in user-facing and system-integrated workflows. In this work, we focus on Markdown formatting, which is ubiquitous in assistants, documentation, and tool-augmented pipelines but still prone to subtle, hard-to-detect errors (e.g., broken lists, malformed tables, inconsistent headings, and invalid code blocks) that can significantly degrade downstream usability. We present FMBench, a benchmark for adaptive Markdown output formatting that evaluates models under a wide range of instruction-following scenarios with diverse structural requirements. FMBench emphasizes real-world formatting behaviors such as multi-level organization, mixed content (natural language interleaved with lists/tables/code), and strict adherence to user-specified layout constraints. To improve Markdown compliance without relying on hard decoding constraints, we propose a lightweight alignment pipeline that combines supervised fine-tuning (SFT) with reinforcement learning fine-tuning. Starting from a base model, we first perform SFT on instruction-response pairs, and then optimize a composite objective that balances semantic fidelity with structural correctness. Experiments on two model families (OpenPangu and Qwen) show that SFT consistently improves semantic alignment, while reinforcement learning provides additional gains in robustness to challenging Markdown instructions when initialized from a strong SFT policy. Our results also reveal an inherent trade-off between semantic and structural objectives, highlighting the importance of carefully designed rewards for reliable formatted generation. Code is available at: https://github.com/FudanCVL/FMBench.