字里行间：法律模拟中行为真实性的建模与评估
Reading Between The Lines: Modeling and Evaluating Behavioral Realism in Legal Simulation
浏览论文内容
中文总结 AI 辅助
本研究推出可控法律角色驱动的证词采集模拟器WitnessSim，采用分离行为真实性与教学实用性的评估框架，证实其行为保真度，为法律模拟性能评估提供框架。
中文摘要 AI 辅助
庭审证词采集培训要求律师管控动态的证人行为，然而当前法律人工智能的评估大多聚焦于事实准确性、推理或单条回应的合理性。我们推出WitnessSim，这是一款由可控法律角色驱动的证词采集模拟器。我们采用将行为真实性与教学实用性相分离的评估框架，通过对抗性测试、盲态律师对比及纵向行为轨迹分析来评估真实性。WitnessSim总体维持了合理的行为边界，律师未系统性地偏好原始证词或WitnessSim生成的证词。教学测试显示，证人行为会因提问形式与律师干预发生有意义的改变，且不会统一破坏所分配的角色。这些结果共同展示了法律模拟中行为保真度的模型，并提供了评估其性能的框架。
英文摘要
Deposition training requires attorneys to manage dynamic witness behavior, yet legal-AI evaluations largely focus on factual accuracy, reasoning, or response-level plausibility. We introduce WitnessSim, a deposition simulator driven by controllable legal personas. We use an evaluation framework separating behavioral realism from pedagogical usefulness. We assess realism through adversarial testing, blinded attorney comparison, and analysis of longitudinal behavioral trajectories. WitnessSim generally maintained plausible behavioral boundaries, and attorneys did not systematically prefer either original testimony or WitnessSim generated testimony. Pedagogical tests showed that witness behavior changed meaningfully in response to question form and attorney intervention without uniformly collapsing the assigned persona. Together, these results showcase a model of behavioral fidelity in legal simulations, and provide a framework for evaluating its performance.
发表机构
- Stanford University（斯坦福大学）
机构由 AI 辅助整理，请以论文原文为准。
