AI 中文总结
本文针对学术报告自动生成任务，提出多阶段提示词链方法，在教育领域实验中，该方法成功率100%、ROUGE-L F1达0.507，优于单次提示基线，可降低生成失败与不一致风险。
AI 中文摘要
学术出版物的指数级增长需要有效的信息合成自动化工具，然而简单的单次提示方法往往缺乏复杂合成任务所需的可靠性与质量。本文介绍并实证评估了一种多阶段提示词链方法，作为此类任务更可靠的架构模式。该方法在我们的系统AI SciBrief中实现，用于自动生成学术摘要。我们开展了对比实验，将该提示词链方法的性能与精心优化的单次提示基线进行比较，两个系统均针对“教育”领域的人工撰写“黄金标准”报告进行评估。结果显示可靠性存在显著差异：我们的提示词链方法达到100%的成功率，而优化基线在50%的运行中失败。在质量方面，所提方法也展现出明显优势，达到更高的ROUGE-L F1分数（0.507对比0.486），主要得益于更高的精度。我们得出结论，提示词链是复杂多步骤生成任务更可靠、有效的工程方法，可显著降低整体提示固有的失败与不一致风险。
英文摘要
The exponential growth of scholarly publications requires automated tools for effective information synthesis. However, simple, single-shot prompting methods often lack the reliability and quality required for complex synthesis tasks. This paper introduces and empirically evaluates a multi-stage prompt chaining methodology as a more reliable architectural pattern for such tasks. This approach is implemented in our system, AI SciBrief, which automatically generates scholarly digests. We conducted a comparative experiment, measuring the performance of our prompt chaining method against a carefully optimized single-shot baseline. Both systems were evaluated against a human-authored "gold standard" report for the "Education" domain. The results demonstrate a significant difference in reliability: our prompt chaining method achieved a 100% success rate, whereas the optimized baseline failed in 50% of its runs. In terms of quality, the proposed method also demonstrated a clear advantage, achieving a superior ROUGE-L F1-score (0.507 vs. 0.486), driven primarily by higher precision. We conclude that prompt chaining is a more dependable and effective engineering approach for complex, multi-step generative tasks, significantly mitigating the risks of failure and inconsistency inherent in monolithic prompts.
CommentsThis is the version of the article accepted for publication in SUMMA 2025 after peer review. The final, published version is available at IEEE Xplore: https://doi.org/10.1109/SUMMA68668.2025.11302303
Journal ref2025 7th International Conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency (SUMMA), Lipetsk, Russian Federation, 2025, pp. 704-710
DOI：10.1109/SUMMA68668.2025.11302303
