持续预训练并非领域自适应所需
Continual Pre-Training is (not) What You Need in Domain Adaption
AI总结：
本文研究领域自适应持续预训练（DACP）对大语言模型（LLMs）法律推理能力的影响，通过台湾法律框架下的实验发现DACP虽增强领域知识但未统一提升所有法律任务性能，提出优化法律AI领域自适应的方向。
摘要：
近年来法律大语言模型（LLMs）的进步通过自动化任务、提高研究精度和支持复杂决策过程，改变了法律研究与实践的格局。然而，由于法律推理的复杂性、对专业语言精确解读的需求以及幻觉风险，有效将LLMs适配到法律领域仍具挑战。本文研究了领域自适应持续预训练（DACP）在提升LLMs法律推理能力方面的效果。通过在台湾法律框架下的法律推理任务系列实验，我们证明DACP虽增强领域特定知识，但未统一提升所有法律任务的性能。我们讨论了DACP涉及的权衡，尤其是其对模型泛化性和提示任务性能的影响，并提出未来研究方向以优化法律AI的领域自适应策略。
英文摘要：
The recent advances in Legal Large Language Models (LLMs) have transformed the landscape of legal research and practice by automating tasks, enhancing research precision, and supporting complex decision-making processes. However, effectively adapting LLMs to the legal domain remains challenging due to the complexity of legal reasoning, the need for precise interpretation of specialized language, and the potential for hallucinations. This paper examines the efficacy of Domain-Adaptive Continual Pre-Training (DACP) in improving the legal reasoning capabilities of LLMs. Through a series of experiments on legal reasoning tasks within the Taiwanese legal framework, we demonstrate that while DACP enhances domain-specific knowledge, it does not uniformly improve performance across all legal tasks. We discuss the trade-offs involved in DACP, particularly its impact on model generalization and performance in prompt-based tasks, and propose directions for future research to optimize domain adaptation strategies in legal AI.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
