# IndoSafety: Culturally Grounded Safety for LLMs in Indonesian Languages

arXiv: https://arxiv.org/abs/2506.02573 · HTML: https://mlsanity.com/paper/2506.02573/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 44 references that are in the map.
- First posted on arXiv 3 Jun 2025.

## Builds on (most cited first, 23 of 23)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [BBQ: A Hand-Built Bias Benchmark for Question Answering](https://mlsanity.com/paper/2110.08193/) (2021)
- [ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection](https://mlsanity.com/paper/2203.09509/) (2022)
- [Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions](https://mlsanity.com/paper/2309.07875/) (2023)
- [Toxicity in ChatGPT: Analyzing Persona-assigned Language Models](https://mlsanity.com/paper/2304.05335/) (2023)
- [SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding](https://mlsanity.com/paper/2402.08983/) (2024)
- [Are Large Pre-Trained Language Models Leaking Your Personal Information?](https://mlsanity.com/paper/2205.12628/) (2022)
- [Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM](https://mlsanity.com/paper/2309.14348/) (2023)
- [Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization](https://mlsanity.com/paper/2311.09096/) (2023)
- [Defending LLMs against Jailbreaking Attacks via Backtranslation](https://mlsanity.com/paper/2402.16459/) (2024)
- [Large Language Models Only Pass Primary School Exams in Indonesia: A Comprehensive Test on IndoMMLU](https://mlsanity.com/paper/2310.04928/) (2023)
- [Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective](https://mlsanity.com/paper/2401.06824/) (2024)
- [SafeText: A Benchmark for Exploring Physical Safety in Language Models](https://mlsanity.com/paper/2210.10045/) (2022)
- [IndoCulture: Exploring Geographically-Influenced Cultural Commonsense Reasoning Across Eleven Indonesian Provinces](https://mlsanity.com/paper/2404.01854/) (2024)
- [COPAL-ID: Indonesian Language Reasoning with Local Culture and Nuances](https://mlsanity.com/paper/2311.01012/) (2023)
- [Arabic Dataset for LLM Safeguard Evaluation](https://mlsanity.com/paper/2410.17040/) (2024)
- [Cracking the Code: Multi-domain LLM Evaluation on Real-World Professional Exams in Indonesia](https://mlsanity.com/paper/2409.08564/) (2024)

## Built on by (most cited first, 7 of 7)

- [IndicJR: A Judge-Free Benchmark of Jailbreak Robustness in South Asian Languages](https://mlsanity.com/paper/2602.16832/) (2026)
- [IndicSafe: A Benchmark for Evaluating Multilingual LLM Safety in South Asia](https://mlsanity.com/paper/2603.17915/) (2026)
- [Role-Aware Language Models for Secure and Contextualized Access Control in Organizations](https://mlsanity.com/paper/2507.23465/) (2025)
- [Low-Resource Safety Failures Are Action Failures, Not Representation Failures](https://mlsanity.com/paper/2606.01196/) (2026)
- [AdaCultureSafe: Adaptive Cultural Safety Grounded by Cultural Knowledge in Large Language Models](https://mlsanity.com/paper/2603.08275/) (2026)
- [LLM Safety Alignment in Low-Resource Languages: A Systematic Literature Review](https://mlsanity.com/paper/2608.14626/) (2026)
- [CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systems](https://mlsanity.com/paper/2609.22494/) (2026)

## Abstract (arXiv)

Although region-specific large language models (LLMs) are increasingly developed, their safety remains underexplored, particularly in culturally diverse settings like Indonesia, where sensitivity to local norms is essential and highly valued by the community. In this work, we present IndoSafety, the first high-quality, human-verified safety evaluation dataset tailored for the Indonesian context, covering five language varieties: formal and colloquial Indonesian, along with three major local languages: Javanese, Sundanese, and Minangkabau. IndoSafety is constructed by extending prior safety frameworks to develop a taxonomy that captures Indonesia's sociocultural context. We find that existing Indonesian-centric LLMs often generate unsafe outputs, particularly in colloquial and local language settings, while fine-tuning on IndoSafety significantly improves safety while preserving task performance. Our work highlights the critical need for culturally grounded safety evaluation and provides a concrete step toward responsible LLM deployment in multilingual settings. Warning: This paper contains example data that may be offensive, harmful, or biased.