Prompting the Market? A Large-Scale Meta-Analysis of GenAI in Finance NLP (2022-2025)

2025-09-11

AI Summary

Rapid advancements in financial NLP have outpaced traditional survey methods, hindering timely capture of dynamic research trends. Method: This paper introduces MetaGraph—a novel framework for constructing the first queryable knowledge graph of financial NLP, built from 681 papers published between 2022 and 2025. It integrates large language model–driven literature information extraction, domain-specific ontology modeling, and structured meta-analysis to enable automated, fine-grained tracking of research topics, technical approaches, and methodological evolution. Contributions/Results: (1) We define a formal financial NLP ontology and open-source a fully reproducible knowledge graph construction pipeline; (2) We identify a three-phase evolutionary trajectory—task-driven innovation → critical reflection on LLM limitations → modular system design and multi-technique integration; (3) We release an open analytical platform supporting dynamic querying and trend visualization, substantially enhancing domain awareness and research decision-making efficiency.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Large Language Models (LLMs) have rapidly reshaped financial NLP, enabling new tasks and driving a proliferation of datasets and diversification of data sources. Yet, this transformation has outpaced traditional surveys. In this paper, we present MetaGraph, a generalizable methodology for extracting knowledge graphs from scientific literature and analyzing them to obtain a structured, queryable view of research trends. We define an ontology for financial NLP research and apply an LLM-based extraction pipeline to 681 papers (2022-2025), enabling large-scale, data-driven analysis. MetaGraph reveals three key phases: early LLM adoption and task/dataset innovation; critical reflection on LLM limitations; and growing integration of peripheral techniques into modular systems. This structured view offers both practitioners and researchers a clear understanding of how financial NLP has evolved - highlighting emerging trends, shifting priorities, and methodological shifts-while also demonstrating a reusable approach for mapping scientific progress in other domains.

Problem

• Analyzing evolution of financial NLP with GenAI
• Structuring research trends via knowledge graphs
• Identifying key phases in LLM adoption limitations

Innovation

• Knowledge graph extraction from scientific literature
• LLM-based pipeline for structured data analysis
• Ontology-driven financial NLP research mapping