让大模型在新会话中审查自己生成的内容，能显著提升纠错能力。
Cross-Context Review: Improving LLM Output Quality by Separating Production and Review Sessions
- 用全新会话审查原输出，不访问原始对话历史
- 纠错F1达28.6%，优于其他三种审查方式
- 无需额外工具，适合所有大模型使用
大语言模型在同一次会话中审查自身输出时难以发现错误。本文提出跨上下文审查（Cross-Context Review, CCR），即在无生产对话历史访问权限的新会话中进行审查。通过控制实验，对30个包含150处错误的文本（代码、技术文档、演讲稿）在四种审查条件下测试：同会话自审（SR）、重复自审（SR2）、上下文感知子代理审查（SA）和跨上下文审查（CCR）。共完成超过360次审查，CCR的F1达到28.6%，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）。值得注意的是，重复自审未显著优于单次自审（p=0.11），说明效果提升并非来自重复，而是源于上下文分离。该方法适用于任何模型，无需额外基础设施，仅增加一次会话开销。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。