English(EN) FinEvolveKG: Controlled and Attributable Prompt Evolution for Financial Knowledge Graph Construction

新系统FinEvolveKG改进金融知识图谱构建

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-09 05:00

研究人员开发了FinEvolveKG，一个用于从SEC 10-Ks构建金融知识图谱的新系统。该系统将通用提示块和特定于角色的提示块分开，使用一种称为GEPA的反射优化器，该优化器被限制在特定角色块内。这种方法确保核心规则保持稳定，同时允许有针对性的提示演化，与不受约束的优化方法相比，性能有所提高，方差有所降低。审计表明，生成的三元组可以作为真实数据，并且比不受约束的方法生成的更受欢迎。 AI

影响这项研究引入了一种新颖的知识图谱构建提示优化方法，有望提高金融数据分析的效率和准确性。

排序理由该项目是一篇学术论文，详细介绍了一种新的知识图谱构建方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该项目是一篇学术论文，详细介绍了一种新的知识图谱构建方法。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Abhinav Arun, Jayita Bhattacharyya, Fabrizio Dimino, Bhaskarjit Sarmah, Stefano Pasquali · 2026-11-09 05:00

FinEvolveKG：用于金融知识图谱构建的可控且可归因的提示演化

arXiv:2611.08643v1 Announce Type: new Abstract: Financial institutions construct knowledge graphs (KGs) from shared SEC 10-Ks to serve risk analysis, portfolio management, and investment research, whose analytical needs differ. Extraction must adapt without fragmenting shared gro…

本文如何被排名

报道来源 [1]

FinEvolveKG：用于金融知识图谱构建的可控且可归因的提示演化

相关实体

相关话题