# From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law

arXiv: https://arxiv.org/abs/2506.06391 · HTML: https://mlsanity.com/paper/2506.06391/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 35 references that are in the map.
- First posted on arXiv 5 Jun 2025.

## Builds on (most cited first, 14 of 14)

- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [OR-Bench: An Over-Refusal Benchmark for Large Language Models](https://mlsanity.com/paper/2405.20947/) (2024)
- [ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation](https://mlsanity.com/paper/2310.17389/) (2023)
- [Does Refusal Training in LLMs Generalize to the Past Tense?](https://mlsanity.com/paper/2407.11969/) (2024)
- [The Radicalization Risks of GPT-3 and Advanced Neural Language Models](https://mlsanity.com/paper/2009.06807/) (2020)
- [Don't Say No: Jailbreaking LLM by Suppressing Refusal](https://mlsanity.com/paper/2404.16369/) (2024)
- [Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety](https://mlsanity.com/paper/2503.05021/) (2025)
- [ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails](https://mlsanity.com/paper/2502.13458/) (2025)
- [International Scientific Report on the Safety of Advanced AI (Interim Report)](https://mlsanity.com/paper/2412.05282/) (2024)
- [Refusal Behavior in Large Language Models: A Nonlinear Perspective](https://mlsanity.com/paper/2501.08145/) (2025)
- [Acceptable Use Policies for Foundation Models](https://mlsanity.com/paper/2409.09041/) (2024)
- [Beyond Benchmarks: On The False Promise of AI Regulation](https://mlsanity.com/paper/2501.15693/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) are widely used across sectors, yet their alignment with International Humanitarian Law (IHL) is not well understood. This study evaluates eight leading LLMs on their ability to refuse prompts that explicitly violate these legal frameworks, focusing also on helpfulness - how clearly and constructively refusals are communicated. While most models rejected unlawful requests, the clarity and consistency of their responses varied. By revealing the model's rationale and referencing relevant legal or safety principles, explanatory refusals clarify the system's boundaries, reduce ambiguity, and help prevent misuse. A standardised system-level safety prompt significantly improved the quality of the explanations expressed within refusals in most models, highlighting the effectiveness of lightweight interventions. However, more complex prompts involving technical language or requests for code revealed ongoing vulnerabilities. These findings contribute to the development of safer, more transparent AI systems and propose a benchmark to evaluate the compliance of LLM with IHL.