Cross-Context Review: Improving LLM Output Quality by Separating Production and Review Sessions

Abstract: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). The central result is that a second review helps only when it happens in a fresh session: CCR (F1 28.6%) outperforms a second review in the same session (SR2, 21.7%) robustly, both in the first run (paired t, p<0.001) and in the three-run average (Holm-adjusted p=0.004). This version updates the broader comparisons. Averaged across runs, and excluding one SR run whose records could not be verified, CCR is not significantly ahead of context-aware subagent review (SA, 23.8%; p=0.057) or of a single same-session review (SR, 27.1%; p=0.26); the first version's advantages over these two baselines came from run 1. CCR needs no infrastructure and costs one extra session.

11 pages, 2 figures, 9 tables. v2: central result (a second review in a fresh session beats one in the same session) holds; one SR run excluded as unverifiable; v1 claim that the ranking held in all runs was inaccurate; advantages over SR and SA not significant across runs; corrects citation errors (incl. figures attributed to Tsui 2025 not in that paper); adds AI-use disclosure

Computation and Language (cs.CL)

arXiv:2603.12123 [cs.CL]

(or arXiv:2603.12123v2 [cs.CL] for this version)