# SafeWorld: Geo-Diverse Safety Alignment

arXiv: https://arxiv.org/abs/2412.06483 · HTML: https://mlsanity.com/paper/2412.06483/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 35 of its 43 references that are in the map.
- First posted on arXiv 9 Dec 2024.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)
- LLM alignment / RLHF / preference optimisation / [Safety alignment and jailbreak attacks](https://mlsanity.com/alignment/safety-alignment-and-jailbreak-attacks/)
- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

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

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- [One Embedder, Any Task: Instruction-Finetuned Text Embeddings](https://mlsanity.com/paper/2212.09741/) (2022)
- [ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation](https://mlsanity.com/paper/2310.17389/) (2023)
- [Predictability and Surprise in Large Generative Models](https://mlsanity.com/paper/2202.07785/) (2022)
- [Societal Biases in Language Generation: Progress and Challenges](https://mlsanity.com/paper/2105.04054/) (2021)
- [SafetyBench: Evaluating the Safety of Large Language Models](https://mlsanity.com/paper/2309.07045/) (2023)
- [A Roadmap to Pluralistic Alignment](https://mlsanity.com/paper/2402.05070/) (2024)
- [A Review on Language Models as Knowledge Bases](https://mlsanity.com/paper/2204.06031/) (2022)
- [On Prompt-Driven Safeguarding for Large Language Models](https://mlsanity.com/paper/2401.18018/) (2024)
- [The Art of Saying No: Contextual Noncompliance in Language Models](https://mlsanity.com/paper/2407.12043/) (2024)
- [CultureBank: An Online Community-Driven Knowledge Base Towards Culturally Aware Language Technologies](https://mlsanity.com/paper/2404.15238/) (2024)
- [Ethical Challenges in Data-Driven Dialogue Systems](https://mlsanity.com/paper/1711.09050/) (2017)
- [Extracting Cultural Commonsense Knowledge at Scale](https://mlsanity.com/paper/2210.07763/) (2022)
- [On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark](https://mlsanity.com/paper/2110.08466/) (2021)
- [Massively Multi-Cultural Knowledge Acquisition & LM Benchmarking](https://mlsanity.com/paper/2402.09369/) (2024)
- [Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning](https://mlsanity.com/paper/2109.06860/) (2021)
- [NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly](https://mlsanity.com/paper/2210.08604/) (2022)
- [Embrace Divergence for Richer Insights: A Multi-document Summarization Benchmark and a Case Study on Summarizing Diverse Information from News Articles](https://mlsanity.com/paper/2309.09369/) (2023)
- [Faking Fake News for Real Fake News Detection: Propaganda-loaded Training Data Generation](https://mlsanity.com/paper/2203.05386/) (2022)
- [CulturalTeaming: AI-Assisted Interactive Red-Teaming for Challenging LLMs' (Lack of) Multicultural Knowledge](https://mlsanity.com/paper/2404.06664/) (2024)

## Built on by (most cited first, 11 of 11)

- [CRMArena-Pro: Holistic Assessment of LLM Agents Across Diverse Business Scenarios and Interactions](https://mlsanity.com/paper/2505.18878/) (2025)
- [The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It](https://mlsanity.com/paper/2505.24119/) (2025)
- [An Evaluation of Cultural Value Alignment in LLM](https://mlsanity.com/paper/2504.08863/) (2025)
- [Multimodal Cultural Safety: Evaluation Framework and Alignment Strategies](https://mlsanity.com/paper/2505.14972/) (2025)
- [Toward Robust Non-Transferable Learning: A Survey and Benchmark](https://mlsanity.com/paper/2502.13593/) (2025)
- [AI Agent Behavioral Science](https://mlsanity.com/paper/2506.06366/) (2025)
- [Fair-PP: A Synthetic Dataset for Aligning LLM with Personalized Preferences of Social Equity](https://mlsanity.com/paper/2505.11861/) (2025)
- [InfiCoEvalChain: A Blockchain-Based Decentralized Framework for Collaborative LLM Evaluation](https://mlsanity.com/paper/2602.08229/) (2026)
- [From Preferences to Prejudice: The Role of Alignment Tuning in Shaping Social Bias in Video Diffusion Models](https://mlsanity.com/paper/2510.17247/) (2025)
- [TWGuard: A Case Study of LLM Safety Guardrails for Localized Linguistic Contexts](https://mlsanity.com/paper/2604.16542/) (2026)
- [ROK-FORTRESS: Measuring the Effect of Geopolitical Transcreation for National Security and Public Safety](https://mlsanity.com/paper/2605.14152/) (2026)

## Abstract (arXiv)

In the rapidly evolving field of Large Language Models (LLMs), ensuring safety is a crucial and widely discussed topic. However, existing works often overlook the geo-diversity of cultural and legal standards across the world. To demonstrate the challenges posed by geo-diverse safety standards, we introduce SafeWorld, a novel benchmark specifically designed to evaluate LLMs' ability to generate responses that are not only helpful but also culturally sensitive and legally compliant across diverse global contexts. SafeWorld encompasses 2,342 test user queries, each grounded in high-quality, human-verified cultural norms and legal policies from 50 countries and 493 regions/races. On top of it, we propose a multi-dimensional automatic safety evaluation framework that assesses the contextual appropriateness, accuracy, and comprehensiveness of responses. Our evaluations reveal that current LLMs struggle to meet these criteria. To enhance LLMs' alignment with geo-diverse safety standards, we synthesize helpful preference pairs for Direct Preference Optimization (DPO) alignment training. The preference pair construction aims to encourage LLMs to behave appropriately and provide precise references to relevant cultural norms and policies when necessary. Our trained SafeWorldLM outperforms all competing models, including GPT-4o on all three evaluation dimensions by a large margin. Global human evaluators also note a nearly 20% higher winning rate in helpfulness and harmfulness evaluation. Our code and data can be found here: https://github.com/PlusLabNLP/SafeWorld.