发表机构
Bosch AI Research（博世人工智能研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过JuryBench基准和432K决策，发现LLM模拟陪审员受情感说服、背景匹配和意识形态影响，背景匹配是显著因素，凸显了LLM建模陪审团推理的潜力与风险。
AI 中文摘要
大型语言模型（LLMs）已被用于模拟专业环境中的决策，但其在普通法陪审团审判中的行为仍未得到探索。我们研究了被告的法庭陈述何时以及如何影响LLM模拟陪审员，重点关注说服、意识形态偏见和基于背景的亲和性。为支持分析，我们引入了JuryBench，一个包含美国刑法中有争议刑事案件的标准基准。在每个案件中，被告可以提出各种合理的辩护理由以支持无罪释放或减轻责任。我们固定基本案件，设计不同背景的被告，他们发表具有不同情感诉求或反驳的法庭陈述。模拟了跨意识形态谱系的多样化陪审员。我们检查了20个前沿LLM，总共产生了432K个决策和理由，并量化了判决严重性的变化。我们的发现表明，LLM陪审团模拟呼应了许多人类陪审团的发现。首先，情感说服可能是有害的，因为陪审员可能将其视为有罪或不一致的证据。接下来，我们表明陪审员与被告之间的背景匹配是一个比其他孤立因素更强且显著的因素，并且陪审员通常对相反背景的被告更严厉，对相同背景的被告更宽容。最后，我们发现陪审员的意识形态也强烈影响严重性判断。这些发现凸显了使用LLM模拟陪审团推理的前景和风险，并呼吁进行仔细评估。数据和代码可在以下https URL获取。
英文摘要
LLMs have been used to simulate human decision-making in professional settings, yet their behaviors in common-law jury trials remain unexplored. We study when and how a defendant's courtroom statement affects LLM-simulated jurors, focusing on persuasion, ideological bias, and background-based affinity. To support the analysis, we introduce JuryBench, a benchmark containing controversial criminal cases in U.S. criminal law. In each case, a defendant can claim various plausible justifications to support acquittal or reduced liability. We fix the base case and design defendants of different backgrounds, who give courtroom statements with varying emotional appeal or rebuttal. Jurors with diverse ideological profiles across the spectrum are simulated. We examine 20 frontier LLMs, resulting in a total of 432K decisions and rationales, and quantify changes in verdict severity. Our findings show that LLM-jury simulation echoes many human-jury findings. First, emotional persuasion can be detrimental, since jurors may perceive it as evidence of guilt or inconsistency. Next, we show that background fit between jurors and defendants is a stronger and significant factor than other isolated factors, and that jurors are in general harsher toward opposite-background defendants and lenient toward same-background ones. Finally, we find that juror ideology also strongly shapes severity judgments. These findings highlight both the promise and risks of using LLMs to model jury reasoning and call for careful evaluation. The data and code are available at https://github.com/choyingw/JuryBench
CommentsAccepted to EMNLP 2026
