# Compliance, Capability, and Conflict: Benchmarking Multimodal LLMs under System Messages

arXiv: https://arxiv.org/abs/2608.19207 · HTML: https://mlsanity.com/paper/2608.19207/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 17 of its 26 references that are in the map.
- First posted on arXiv 12 Jun 2026.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

## Builds on (most cited first, 17 of 17)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions](https://mlsanity.com/paper/2404.13208/) (2024)
- [Benchmarking Complex Instruction-Following with Multiple Constraints Composition](https://mlsanity.com/paper/2407.03978/) (2024)
- [Aligning to Thousands of Preferences via System Message Generalization](https://mlsanity.com/paper/2405.17977/) (2024)
- [FOFO: A Benchmark to Evaluate LLMs' Format-Following Capability](https://mlsanity.com/paper/2402.18667/) (2024)
- [Can Large Language Models Understand Real-World Complex Instructions?](https://mlsanity.com/paper/2309.09150/) (2023)
- [MIA-Bench: Towards Better Instruction Following Evaluation of Multimodal LLMs](https://mlsanity.com/paper/2407.01509/) (2024)
- [MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2408.00765/) (2024)
- [Measuring and Controlling Instruction (In)Stability in Language Model Dialogs](https://mlsanity.com/paper/2402.10962/) (2024)
- [MM-IFEngine: Towards Multimodal Instruction Following](https://mlsanity.com/paper/2504.07957/) (2025)
- [SysBench: Can Large Language Models Follow System Messages?](https://mlsanity.com/paper/2408.10943/) (2024)
- [SoFA: Shielded On-the-fly Alignment via Priority Rule Following](https://mlsanity.com/paper/2402.17358/) (2024)
- [Empowering Reliable Visual-Centric Instruction Following in MLLMs](https://mlsanity.com/paper/2601.03198/) (2026)

## Abstract (arXiv)

Production deployments of Multimodal Large Language Models (MLLMs) increasingly rely on system messages to govern model behavior. Yet existing benchmarks either evaluate constraints in text only or embed them into the user turn, leaving system-message adherence in multimodal contexts largely unmeasured; they also leave open whether compliance comes at the cost of foundational vision-language capabilities. We introduce VSysBench, a benchmark built on MMVet-v2 that organizes constraints into 5 main categories and 22 sub-categories, ranging from textual directives in visual contexts to fully vision-grounded ones, each paired with a misaligned counterpart that stress-tests the instructional hierarchy. VSysBench scores each response jointly along two axes, constraint compliance and answer correctness, via the Joint Satisfaction Rate (JSR) and Cross-Constraint Sensitivity (CCS). Across 16 MLLMs, we find that imposing system messages substantially erodes base task accuracy, that compliance collapses under user conflict for open-weight models while remaining stable for top proprietary ones, and that vision-grounded constraints are the hardest category for every model.