# Visual Compliance via Executable Safety Rule Entailment

arXiv: https://arxiv.org/abs/2609.18328 · HTML: https://mlsanity.com/paper/2609.18328/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 59 references that are in the map.
- First posted on arXiv 16 Sep 2026.

## Builds on (most cited first, 30 of 35)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [Depth Anything 3: Recovering the Visual Space from Any Views](https://mlsanity.com/paper/2511.10647/) (2025)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [ViperGPT: Visual Inference via Python Execution for Reasoning](https://mlsanity.com/paper/2303.08128/) (2023)
- [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://mlsanity.com/paper/2210.02406/) (2022)
- [Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning](https://mlsanity.com/paper/2205.09712/) (2022)
- [Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations](https://mlsanity.com/paper/2411.10414/) (2024)
- [ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time](https://mlsanity.com/paper/2410.06625/) (2024)
- [LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models](https://mlsanity.com/paper/2406.05113/) (2024)
- [R2-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoning](https://mlsanity.com/paper/2407.05557/) (2024)
- [Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning](https://mlsanity.com/paper/2409.12452/) (2024)
- [LabSafety Bench: Benchmarking LLMs on Safety Issues in Scientific Labs](https://mlsanity.com/paper/2410.14182/) (2024)
- [MLLM-as-a-Judge for Image Safety without Human Labeling](https://mlsanity.com/paper/2501.00192/) (2024)
- [GENOME: GenerativE Neuro-symbOlic visual reasoning by growing and reusing ModulEs](https://mlsanity.com/paper/2311.04901/) (2023)
- [LASER: A Neuro-Symbolic Framework for Learning Spatial-Temporal Scene Graphs with Weak Supervision](https://mlsanity.com/paper/2304.07647/) (2023)
- [GSPR: Aligning LLM Safeguards as Generalizable Safety Policy Reasoners](https://mlsanity.com/paper/2509.24418/) (2025)
- [NAVER: A Neuro-Symbolic Compositional Automaton for Visual Grounding with Explicit Logic Reasoning](https://mlsanity.com/paper/2502.00372/) (2025)
- [Prompt Sentiment: The Catalyst for LLM Change](https://mlsanity.com/paper/2503.13510/) (2025)
- [Self-Critique and Refinement for Faithful Natural Language Explanations](https://mlsanity.com/paper/2505.22823/) (2025)
- [Investigating the Shortcomings of LLMs in Step-by-Step Legal Reasoning](https://mlsanity.com/paper/2502.05675/) (2025)
- [Better Safe Than Sorry? Overreaction Problem of Vision Language Models in Visual Emergency Recognition](https://mlsanity.com/paper/2505.15367/) (2025)
- [Are Large Pre-trained Vision Language Models Effective Construction Safety Inspectors?](https://mlsanity.com/paper/2508.11011/) (2025)
- [PORT: Preference Optimization on Reasoning Traces](https://mlsanity.com/paper/2406.16061/) (2024)
- [Zero-Shot Defense Against Toxic Images via Inherent Multimodal Alignment in LVLMs](https://mlsanity.com/paper/2503.00037/) (2025)

## Abstract (arXiv)

Recent advances in LLMs and VLMs have enabled safety systems to reason beyond simple risk patterns toward more contextual and semantic safety concerns. However, as risk patterns continue to evolve and safety rules become more complex, existing training-based end-to-end safeguards face persistent challenges in adaptability and explainable reasoning over complex safety rules. To address these challenges, we propose GuardEn (Guarding by Safety Rule Entailment), an executable safeguard framework that decomposes safety policies into atomic propositions through Safety-Rule Compilation, modeling their composition as executable code. At test time, Scene-Grounded Execution instantiates these atomic propositions with contextual visual information derived from scene graphs, enabling rule-grounded and interpretable safety reasoning. Experiments on SafetyVisionBench demonstrate the effectiveness of programmable safeguard for complex visual safety assessment, achieving an average improvement of 9.8 F1 points over the strongest baseline.