arXiv cs.CL· Abhinav Arun, Jayita Bhattacharyya, Fabrizio Dimino, Bhaskarjit Sarmah, Stefano Pasquali·· 11 小时前AI 评分31
FinEvolveKG：面向金融知识图谱构建的可控可归因提示词演化
FinEvolveKG: Controlled and Attributable Prompt Evolution for Financial Knowledge Graph Construction
AI 导读
FinEvolveKG 将知识图谱构建提示词拆分为可复用的通用块与 persona 策略块，并把反思式提示词优化器 GEPA 的修改机械限制在指定块内，使通用块在 persona 适配中保持字节级不变。
正文 · 原文
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 grounding, typing, and temporal rules. Hand-authored persona prompts and fine-tuning add cost. Weight-free prompt optimization offers an alternative, but unconstrained evolution of a monolithic prompt can rewrite shared rules alongside persona guidance, obscuring changes and complicating review. We introduce FinEvolveKG, a KG-construction harness separating reusable general and persona-policy blocks and mechanically confining GEPA, a reflective prompt optimizer, to the designated block. During persona adaptation, the approved general block remains byte-stable and every optimizer edit is localized to a separately versioned persona policy. A dual objective balances generic temporal-KG quality with persona-relevant facts, motifs, and multi-hop connectivity. We evaluate five mutation scopes on ticker-disjoint 10-K splits, with three seeds for the persona-conditioned arms (v3-v5) across three personas. On the three-seed mean, the complete two-stage block-constrained workflow (v4) improves over the frozen prompt baseline (v1) by 19.4-30.9% and over the tested unconstrained full-prompt workflow (v5) by 2.2-6.4%, leading v5 on both objective components and winning all nine paired-seed comparisons with the lowest seed variance in every persona. Without further optimization, v4 also exceeds v5 across all evaluated out-of-distribution (OOD) shifts. An SME audit supports using the generated triplets as ground truth; a blinded two-SME audit favors v4 over v5 in 70.1% of contrast-enriched judgments. These results show that mechanically attributable evolution can coexist with strong empirical performance, without attributing the gains causally to the boundary.
| Comments: | 8 pages, 1 figure, 5 tables |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.08643 [cs.CL] |
| (or arXiv:2611.08643v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.08643 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Abhinav Arun [view email]
[v1]
Thu, 5 Nov 2026 19:44:51 UTC (24 KB)
来源：arXiv cs.CL · arxiv.org