mlsanityData to 13 Oct 2026

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

arXiv 2603.12123 ↗First posted 12 Mar 2026cs.CLcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 13 Oct 2026). Builds on 13 of its 26 references that are in the map. First posted on arXiv 12 Mar 2026.

Builds on

13 of 26 references.

References · 13

  1. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,412
  2. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,367
  3. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,758
  4. 2023Towards Understanding Sycophancy in Language Modelscited by 1,018
  5. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,001
  6. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 983
  7. 2023ChatDev: Communicative Agents for Software Developmentcited by 901
  8. 2024LLM Evaluators Recognize and Favor Their Own Generationscited by 664
  9. 2024When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMscited by 233
  10. 2024Understanding the Dark Side of LLMs' Intrinsic Self-Correctioncited by 42
  11. 2024Anchoring Bias in Large Language Models: An Experimental Studycited by 37
  12. 2025When Identity Skews Debate: Anonymization for Bias-Reduced Multi-Agent Reasoningcited by 20
1 more
  1. 2024LLM-as-an-Interviewer: Beyond Static Testing Through Dynamic LLM Evaluationcited by 13

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026More Rounds, More Noise: Why Multi-Turn Review Fails to Improve Cross-Context Verificationcited by 4
  2. 2026Cross-Context Verification: Hierarchical Detection of Benchmark Contamination through Session-Isolated Analysiscited by 2
  3. 2026Self-Preference Is Weak or Absent in Verifiable Instruction-Following Revision: A Four-Model Test Under Genuine Authorshipcited by 2
  4. 2026When Does a Second Model Help? Cross-Model Review in LLM Verificationcited by 1
  5. 2026Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discoverycited by 0