# LegalMidm: Use-Case-Driven Legal Domain Specialization for Korean Large Language Model

arXiv: https://arxiv.org/abs/2604.25297 · HTML: https://mlsanity.com/paper/2604.25297/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 28 Apr 2026.

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

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning](https://mlsanity.com/paper/2308.08747/) (2023)
- [CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution](https://mlsanity.com/paper/2401.03065/) (2024)
- [Large Language Models in Finance: A Survey](https://mlsanity.com/paper/2311.10723/) (2023)
- [Continual Pre-training of Language Models](https://mlsanity.com/paper/2302.03241/) (2023)
- [Security and Privacy Challenges of Large Language Models: A Survey](https://mlsanity.com/paper/2402.00888/) (2024)
- [XuanYuan 2.0: A Large Chinese Financial Chat Model with Hundreds of Billions Parameters](https://mlsanity.com/paper/2305.12002/) (2023)
- [KMMLU: Measuring Massive Multitask Language Understanding in Korean](https://mlsanity.com/paper/2402.11548/) (2024)
- [Investigating Continual Pretraining in Large Language Models: Insights and Implications](https://mlsanity.com/paper/2402.17400/) (2024)
- [Lawyer LLaMA Technical Report](https://mlsanity.com/paper/2305.15062/) (2023)
- [Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2502.10708/) (2025)
- [HAE-RAE Bench: Evaluation of Korean Knowledge in Language Models](https://mlsanity.com/paper/2309.02706/) (2023)
- [D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models](https://mlsanity.com/paper/2406.01375/) (2024)
- [LawLLM: Law Large Language Model for the US Legal System](https://mlsanity.com/paper/2407.21065/) (2024)
- [Fine-tuning and Utilization Methods of Domain-specific LLMs](https://mlsanity.com/paper/2401.02981/) (2024)
- [Efficient Continual Pre-training for Building Domain Specific Large Language Models](https://mlsanity.com/paper/2311.08545/) (2023)
- [Tag-LLM: Repurposing General-Purpose LLMs for Specialized Domains](https://mlsanity.com/paper/2402.05140/) (2024)
- [Agentic Systems: A Guide to Transforming Industries with Vertical AI Agents](https://mlsanity.com/paper/2501.00881/) (2025)
- [System Prompt Optimization with Meta-Learning](https://mlsanity.com/paper/2505.09666/) (2025)
- [Bringing order into the realm of Transformer-based language models for artificial intelligence and law](https://mlsanity.com/paper/2308.05502/) (2023)
- [LegiLM: A Fine-Tuned Legal Language Model for Data Compliance](https://mlsanity.com/paper/2409.13721/) (2024)
- [Towards Best Practices for Open Datasets for LLM Training](https://mlsanity.com/paper/2501.08365/) (2025)

## Abstract (arXiv)

In recent years, the rapid proliferation of open-source large language models (LLMs) has spurred efforts to turn general-purpose models into domain specialists. However, many domain-specialized LLMs are developed using datasets and training protocols that are not aligned with the nuanced requirements of real-world applications. In the legal domain, where precision and reliability are essential, this lack of consideration limits practical utility. In this study, we propose a systematic training framework grounded in the practical needs of the legal domain, with a focus on Korean law. We introduce LegalMidm, a Korean legal-domain LLM, and present a methodology for constructing high-quality, use-case-driven legal datasets and optimized training pipelines. Our approach emphasizes collaboration with legal professionals and rigorous data curation to ensure relevance and factual accuracy, and demonstrates effectiveness in key legal tasks.