GAIJ - Graph-bound AI Journalism in Financial Fraud

Large-language models (LLMs), most famously nowadays, ChatGPT, are at the forefront of interest in research in Artificial Intelligence. LLMs have the ability to process vast amounts of textual data, including unstructured information from diverse sources such as news articles, social media, and, most importantly financial reports. They can unveil patterns in large datasets that are inaccessible to a human reader, either because of the sheer size of the databases or because of the subtle connections between various elements in text that might not be obvious to an uneducated eye. Similar to how a human mind seeks to puzzle evidence together, LLMs can be used to construct a network or graph of interaction between companies and other actors, and therein try to assess the relevant actors immersed in suspicious activities. This project aims to harness the potential of LLMs, big or small, in unveiling links in financial reports, tax declarations, and bank statements, that prove to be illegal or have been made with ill intent. It is crucial to use burgeoning technologies, like LLMs, to aid us in tracking and identifying illegitimate financial activities.

Illicit financial transactions constitute a serious ethical challenge to the proper functioning of society. Various regulatory frameworks enforce banks, companies, and governments to keep checks on illicit financial flows, yet in gross amount, these still comprise a significant portion of the world's trade value. At the forefront of exposing malicious entities involved in non-sustainable activities are investigative journalists. Yet assessing financial data in a digital world is a strenuous task. GAIJ – Graph-bound Artificial Intelligence Journalism – is a project centred on utilising modern open-source Large Language Models (LLMs) to classify illicit transactions in financial and tax records. The target of this pilot project is to develop a prototype open-source Artificial Intelligence (AI) model that examines and classifies transaction data, creating a graph of suspicious interactions between companies. This proposal is at the forefront of current research on the application of AI tools in Investigative Journalism. One core and distinctly unconventional aspect of GAIJ is that it utilised LLMs to classify data, not generate text. GAIJ uses not one, but a collection of LLMs to generate text regarding interactions between companies and classify actual interactions as regular or suspicious. This is the most striking, cutting-edge method employed in GAIJ, and thus naturally also the most challenging. Various questions and research avenues are open: Are LLMs capable of serving as classification tools, particularly of unlikely events? Are LLMs sufficiently powerful to unravel relevant information from interaction data like financial transactions? Are they able to discern between regular and illicit activities? On a large scale, GAIJ falls into the present pertinent scope of understanding what role AI models have in serving as tools to improve society and how can they aid, for example, journalists in untangling unsustainable financial practices from companies.