FinEvolveKG: Controlled and Attributable Prompt Evolution for Financial Knowledge Graph Construction
Organizations: Domyn, New York, USA · Domyn, Bengaluru, India · Domyn, Gurugram, India
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.
Figures & tables
| Arm | Mutable | Fixed | GT data | Selection objective |
|---|---|---|---|---|
| v1 | – | both at seed | – | no search |
| v2 | general | persona seed | generic | |
| v3 | persona | general seed | persona (all) | |
| v4 | persona | general v2 | persona (all) | |
| v5 | full prompt | – | persona (all) |
| Persona | Owns | Key types / relations | Example motif |
|---|---|---|---|
| risk_analyst | downside & compliance | RISK_FACTOR , LITIGATION , ORG_REG ; Negatively_Impacts , Faces , Regulates | RISK_FACTOR Negatively_Impacts FIN_METRIC |
| portfolio_mgr | quantitative performance | FIN_METRIC , FIN_INST , SEGMENT ; Discloses , Guides_On | SEGMENT Discloses FIN_METRIC |
| investment_researcher | strategic / competitive | PRODUCT , COMP , SECTOR ; Produces , Partners_With | ORG Partners_With COMP |
| Component | Setting |
|---|---|
| Train (IT, 2024) | AAPL, ACN, ADBE, CRM, AVGO, INTC, ORCL, CSCO |
| Validation (IT, 2024) | AMAT, IBM, INTU, LRCX |
| Test (IT, 2024) | AMD, MSFT, NVDA, MU, NOW, PLTR, QCOM, TXN |
| OOD sector (2024) | Financials: AXP, MA, SCHW, V; Health Care: ABT, AMGN, BMY, ISRG; Consumer Staples: CL, KMB, KO, MDLZ |
| OOD temporal | AAPL, IBM, MSFT, NVDA (IT, 2025) |
| OOD combined | AXP, MA, SCHW, V (Financials, 2025) |
| Persona | Arm | |||
|---|---|---|---|---|
| Risk analyst | v1 | .7187 | .1186 | .4186 |
| v2 | .8108 | .1678 | .4893 | |
| v3 | ||||
| v4 | ||||
| v5 | ||||
| Portfolio manager | v1 | .7258 | .2061 | .4659 |
| In-domain | Sector shift (’24) | Temporal shift | Sector + temporal | ||||
|---|---|---|---|---|---|---|---|
| Persona | Arm | IT ’24 | Financials | Health Care | Consumer Staples | IT ’25 | Financials ’25 |
| Risk analyst | v1 | .4186 | .3458 | .3629 | .3446 | .4021 | .3900 |
| v2 | .4893 | .4177 | .4349 | .4261 | .4883 | .4724 | |
| v3 | .4978 | .3925 | .3683 | .3891 | .4698 | .4383 | |
| v4 | .5331 | .4344 | .4552 | .4427 | .5256 | .5039 | |
| v5 | .4979 | .3914 | .4098 | .3980 | .4695 | .4479 | |
KG Construction
Knowledge graph construction turns text, tables, images, and databases into structured entities and relationships that machines can query and reason over.
See all 207 papers