# Korean Culture into LLM Alignment: Toward Cultural Coherence

arXiv: https://arxiv.org/abs/2606.06797 · HTML: https://mlsanity.com/paper/2606.06797/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 17 of its 24 references that are in the map.
- First posted on arXiv 5 Jun 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## 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)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models](https://mlsanity.com/paper/2308.01263/) (2023)
- [OR-Bench: An Over-Refusal Benchmark for Large Language Models](https://mlsanity.com/paper/2405.20947/) (2024)
- [Cultural Bias and Cultural Alignment of Large Language Models](https://mlsanity.com/paper/2311.14096/) (2023)
- [X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents](https://mlsanity.com/paper/2504.13203/) (2025)
- [KMMLU: Measuring Massive Multitask Language Understanding in Korean](https://mlsanity.com/paper/2402.11548/) (2024)
- [KoBBQ: Korean Bias Benchmark for Question Answering](https://mlsanity.com/paper/2307.16778/) (2023)
- [EXAONE 3.5: Series of Large Language Models for Real-world Use Cases](https://mlsanity.com/paper/2412.04862/) (2024)
- [Understand, Solve and Translate: Bridging the Multilingual Mathematical Reasoning Gap](https://mlsanity.com/paper/2501.02448/) (2025)
- [KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledge](https://mlsanity.com/paper/2402.13605/) (2024)
- [EXAONE 3.0 7.8B Instruction Tuned Language Model](https://mlsanity.com/paper/2408.03541/) (2024)
- [CAGE: A Framework for Culturally Adaptive Red-Teaming Benchmark Generation](https://mlsanity.com/paper/2602.20170/) (2026)
- [STAR-Teaming: A Strategy-Response Multiplex Network Approach to Automated LLM Red Teaming](https://mlsanity.com/paper/2604.18976/) (2026)

## Built on by (most cited first, 2 of 2)

- [Pluralis v0.1: Towards a Multicultural, Multimodal, Multilingual Benchmark for AI Risk and Reliability](https://mlsanity.com/paper/2607.06196/) (2026)
- [Synthetic Cultural Agents from Aggregate Anchors](https://mlsanity.com/paper/2610.06562/) (2026)

## Abstract (arXiv)

Cultural-aspect work on large language models is dominated by a negative target: which outputs to suppress. We argue that a constructive counterpart is also needed, a working definition of what a culturally coherent response is rather than only what it must avoid, and instantiate it for Korean. We design an alignment-data pipeline around a prompt-based LLM seed generator that expands a Korean harm taxonomy, with a Korean-culturally-adapted safe-response policy at its centre: a per-category guideline grounded in Korean legal frameworks, social norms, and interpretive conventions, against which three frontier models each produce a candidate response. DPO fine-tuning on the resulting triplets improves the Korean cultural safe rate across six open-weight LLMs while causing no large degradation on Korean general-capability benchmarks, and qualitative outputs show fine-tuned models naming Korean statutes and institutional procedures and, where appropriate, supplying constructive Korean-context information alongside refusal.