Large language models struggle to catch errors in their own outputs when the review happens in the same session that produced them. This paper introduces Cross-Context Review (CCR), a straightforward method where the review is conducted in a fresh session with no access to the production conversation history. We ran a controlled experiment: 30 artifacts (code, technical documents, presentation scripts) with 150 injected errors, tested under four review conditions -- same-session Self-Review (SR), repeated Self-Review (SR2), context-aware Subagent Review (SA), and Cross-Context Review (CCR). Over 360 reviews, CCR reached an F1 of 28.6%, outperforming SR (24.6%, p=0.008, d=0.52), SR2 (21.7%, p<0.001, d=0.72), and SA (23.8%, p=0.004, d=0.57). The SR2 result matters most for interpretation: reviewing twice in the same session did not beat reviewing once (p=0.11), which rules out repetition as an explanation for CCR's advantage. The benefit comes from context separation itself. CCR works with any model, needs no infrastructure, and costs only one extra session.

翻译：大型语言模型在审查自身于同一会话中生成的输出时，难以有效识别其中的错误。本文提出跨上下文审查（CCR）这一简洁方法，即在无法访问生成对话历史的全新会话中进行审查。我们开展了一项对照实验：对包含150个注入错误的30件生成物（代码、技术文档、演示文稿脚本）在四种审查条件下进行测试——同会话自我审查（SR）、重复自我审查（SR2）、上下文感知子代理审查（SA）以及跨上下文审查（CCR）。在超过360次审查中，CCR取得了28.6%的F1分数，显著优于SR（24.6%，p=0.008，d=0.52）、SR2（21.7%，p<0.001，d=0.72）和SA（23.8%，p=0.004，d=0.57）。其中SR2的结果对解读最为关键：在同一会话中进行两次审查并未优于单次审查（p=0.11），这排除了重复操作作为CCR优势的解释。其效益源于上下文分离本身。CCR兼容任何模型，无需额外基础设施，仅需增加一次会话成本。