PoliLegalLM: A Technical Report on a Large Language Model for Political and Legal Affairs

2026-04-19

AI Summary

This work addresses key challenges faced by general-purpose large language models in the legal domain—namely, citation hallucination, insufficient knowledge coverage, and weak structured reasoning—by proposing a domain-specific large language model tailored for political and legal affairs. The authors introduce a unified training paradigm that integrates continual pretraining on high-quality legal corpora, progressive supervised fine-tuning, and preference-based reinforcement learning to systematically enhance the model’s factual accuracy, task alignment, and reasoning capabilities. Experimental results demonstrate that the proposed model significantly outperforms same-scale baselines on established benchmarks such as LawBench and LexEval, as well as on PoliLegal, a real-world legal dataset, exhibiting superior practicality and reliability in authentic legal applications.

Technology Category

• Natural Language Processing: (Large) Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Philosophy and Ethics of AI: AI & Law, Justice, Regulation & Governance

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Large language models (LLMs) have achieved remarkable success in general-domain tasks, yet their direct application to the legal domain remains challenging due to hallucinated legal citations, incomplete knowledge coverage, and weak structured reasoning. To address these issues, we propose PoliLegalLM, a domain-specific large language model tailored for political and legal applications. Our approach adopts a unified training framework that integrates continued pretraining, progressive supervised fine-tuning, and preference-based reinforcement learning to jointly enhance legal knowledge grounding, task alignment, and reasoning capability. We construct a large-scale, high-quality legal corpus and design a structured post-training pipeline, enabling the model to effectively learn domain-specific knowledge and adapt to diverse legal tasks. We evaluate PoliLegalLM on three representative benchmarks, including LawBench, LexEval, and a real-world dataset, PoliLegal. Experimental results demonstrate that PoliLegalLM achieves strong and consistent performance, outperforming competitive models of similar scale and remaining highly competitive with significantly larger models, while achieving the best results on real-world legal scenarios. These results highlight the effectiveness of our training paradigm and the practical value of domain-specific LLMs for real-world legal applications.

Problem

• legal hallucination
• knowledge coverage
• structured reasoning
• domain-specific LLM
• legal applications

Innovation

• domain-specific LLM
• structured reasoning
• legal knowledge grounding
• preference-based reinforcement learning
• progressive supervised fine-tuning