LLM-Enhanced Dynamic Financial Knowledge Graphs for Cross-Entity Signal Propagation and alpha discovery

2026-07-12

AI Summary

This study addresses the limitation of traditional financial NLP approaches that capture only direct sentiment toward individual firms while neglecting the cross-entity propagation of financial events through corporate networks such as supply chains and competitive relationships. The authors propose a large language model–based method that transforms unstructured text into structured economic state-change events, constructs a dynamic financial knowledge graph, and incorporates a community-aware signal propagation mechanism to enhance information diffusion within dynamically identified economic communities. They introduce two novel networked financial signals—Community Information Surprise (CIS) and Propagated Information Surprise (PIS)—to enable dynamic detection and incremental forecasting of emerging investment ecosystems. Empirical results demonstrate that the proposed approach significantly outperforms conventional sentiment and direct event signals in terms of information coefficient and long–short Sharpe ratio, maintaining robustness under sparse network structures and real-world market conditions.

Abstract

Financial information rarely affects a single company in isolation. Earnings surprises, capital expenditure changes, supply constraints, and guidance revisions can propagate through networks of suppliers, customers, competitors, and technology ecosystems. Traditional financial NLP primarily measures document-level sentiment for the directly mentioned company and often ignores cross-entity information diffusion. This paper develops an LLM-based financial measurement and signal propagation framework. The LLM converts unstructured financial documents into structured economic state-change events and extracts explicit and implicit corporate relationships to construct a dynamic financial knowledge graph. Event signals are then propagated through the estimated network using a community-aware mechanism, allowing information to diffuse more strongly within dynamically detected economic communities than across community boundaries. We introduce Community Information Surprise, CIS, and Propagated Information Surprise, PIS, as network-based financial signals and develop corresponding econometric tests. Controlled simulations with time-varying economic communities show that the framework accurately recovers latent network structure, detects the emergence of new investment ecosystems, and generates propagated signals with incremental predictive power beyond sentiment and direct LLM event signals. Across repeated simulations, community-aware propagation achieves the strongest rank information coefficient and long-short Sharpe ratio among five nested benchmarks.A second Russell 1000 calibrated simulation confirms that the main results persist under sparser networks, heterogeneous news coverage, realistic large-cap volatility, and smaller effect sizes.

Problem

• cross-entity signal propagation
• financial knowledge graph
• information diffusion
• alpha discovery
• economic networks

Innovation

• LLM-enhanced knowledge graph
• cross-entity signal propagation
• community-aware diffusion
• dynamic financial networks
• information surprise