发表机构
Microsoft; Beijing Jiaotong University（微软; 北京交通大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对企业信息抽取中用户个性化需求，提出自我元进化框架，通过双循环为每个用户适配提示，在292用户基准上成功率74.58%，超基线13.56个百分点，人工评估中71%对比获胜。
AI 中文摘要
大型语言模型（LLMs）正越来越多地被部署用于企业信息抽取（IE），在此场景中，同一文档必须针对不同用户进行不同的重新组织。然而，现有的提示优化方法依赖于针对全局目标优化的单一提示，这与真实工作场所中固有的用户异质性不一致。我们将企业信息抽取问题形式化为在交互反馈下的逐用户提示适配问题，并提出自我元进化（Self-Meta-Evolve）方法，这是一种分层框架，为每个用户维护一个专属提示，并通过双循环过程持续优化：内循环基于个性条件反馈编辑结构化提示，外循环通过提炼成功的编辑模式来进化元提示本身。为了支持可扩展的训练和评估，我们发布了一个基于个性的信息抽取基准，包含292个模拟企业用户，并配有一个基于O*NET职业分类法的可复现个性生成流程。在该基准上，自我元进化方法达到了74.58%的成功率，比最强的提示优化基线高出13.56个百分点，并且仅需两次迭代即可达到52.54%的成功率。一项由二十名真实专业人士参与的双盲人工研究进一步证实，我们框架适配的提示在71%的成对比较中胜过静态基线。
英文摘要
Large language models (LLMs) are increasingly deployed for enterprise information extraction (IE), where the same document must be reorganized differently for each user. Existing prompt optimization methods, however, rely on a single prompt optimized against a global objective, which is misaligned with the inherent user heterogeneity of real workplaces. We formulate enterprise IE as per-user prompt adaptation under interaction feedback and propose Self-Meta-Evolve, a hierarchical framework that maintains a dedicated prompt for each user and continuously refines it through a dual-loop process: an inner loop that edits structured prompts based on persona-conditioned feedback, and an outer loop that evolves the meta-prompt itself by distilling successful editing patterns. To enable scalable training and evaluation, we release a persona-driven IE benchmark of 292 simulated enterprise users, paired with a reproducible persona-generation pipeline grounded in O*NET occupational taxonomies. On this benchmark, Self-Meta-Evolve achieves a 74.58% success rate, outperforming the strongest prompt-optimization baseline by 13.56 absolute points, and reaches 52.54\% within only two iterations. A double-blind human study with twenty real professionals further confirms that prompts adapted by our framework win against static baselines in 71% of pairwise comparisons.
Comments16 pages, 4 figures, Findings of AACL-IJCNLP 2026
