LawFlow：律师思维过程的收集与模拟

摘要

法律从业者，尤其是初入职场者，常面临复杂且高风险的挑战，这些任务需要具备适应性强、情境敏感的推理能力。尽管人工智能在辅助法律工作方面展现出潜力，但当前的数据集和模型多局限于孤立的子任务，未能涵盖实际执业中所需的端到端决策过程。为填补这一空白，我们推出了LawFlow，这是一个基于真实商业实体设立场景、由训练有素的法律学生完成的完整端到端法律工作流程数据集。与以往专注于输入输出对或线性思维链的数据集不同，LawFlow捕捉了动态、模块化及迭代的推理过程，反映了法律实践中存在的模糊性、修订需求及客户适应性策略。通过LawFlow，我们对比了人类与大型语言模型（LLM）生成的工作流程，揭示了二者在结构、推理灵活性及计划执行上的系统性差异。人类工作流程倾向于模块化与适应性，而LLM工作流程则更为序列化、详尽且对下游影响不够敏感。我们的研究还表明，法律专业人士更倾向于让AI承担支持性角色，如头脑风暴、识别盲点及提出替代方案，而非执行复杂的端到端工作流程。基于这些发现，我们提出了一套设计建议，这些建议根植于实证观察，旨在通过混合规划、适应性执行及决策点支持，使AI辅助与人类追求清晰、完整、创意及效率的目标相契合。我们的成果既凸显了LLM在支持复杂法律工作流程上的现有局限，也为开发更具协作性、推理意识的法律AI系统指明了方向。所有数据与代码均可在我们的项目页面（https://minnesotanlp.github.io/LawFlow-website/）获取。

English

Legal practitioners, particularly those early in their careers, face complex, high-stakes tasks that require adaptive, context-sensitive reasoning. While AI holds promise in supporting legal work, current datasets and models are narrowly focused on isolated subtasks and fail to capture the end-to-end decision-making required in real-world practice. To address this gap, we introduce LawFlow, a dataset of complete end-to-end legal workflows collected from trained law students, grounded in real-world business entity formation scenarios. Unlike prior datasets focused on input-output pairs or linear chains of thought, LawFlow captures dynamic, modular, and iterative reasoning processes that reflect the ambiguity, revision, and client-adaptive strategies of legal practice. Using LawFlow, we compare human and LLM-generated workflows, revealing systematic differences in structure, reasoning flexibility, and plan execution. Human workflows tend to be modular and adaptive, while LLM workflows are more sequential, exhaustive, and less sensitive to downstream implications. Our findings also suggest that legal professionals prefer AI to carry out supportive roles, such as brainstorming, identifying blind spots, and surfacing alternatives, rather than executing complex workflows end-to-end. Building on these findings, we propose a set of design suggestions, rooted in empirical observations, that align AI assistance with human goals of clarity, completeness, creativity, and efficiency, through hybrid planning, adaptive execution, and decision-point support. Our results highlight both the current limitations of LLMs in supporting complex legal workflows and opportunities for developing more collaborative, reasoning-aware legal AI systems. All data and code are available on our project page (https://minnesotanlp.github.io/LawFlow-website/).

LawFlow：律师思维过程的收集与模拟

LawFlow : Collecting and Simulating Lawyers' Thought Processes

摘要

Support