Towards automated data analysis: A guided framework for LLM-based risk estimation
This work addresses the time-consuming and complex problem of manual dataset risk analysis for organizations integrating LLMs into critical decision-making pipelines, offering an incremental step towards automation.
This paper proposes a framework that integrates Large Language Models (LLMs) with human guidance to automate dataset risk estimation. The LLM identifies data properties, proposes clustering, generates code, and interprets results, while a human supervisor ensures alignment and integrity. A proof of concept demonstrates its feasibility in risk assessment.
Large Language Models (LLMs) are increasingly integrated into critical decision-making pipelines, a trend that raises the demand for robust and automated data analysis. Current approaches to dataset risk analysis are limited to manual auditing methods which involve time-consuming and complex tasks, whereas fully automated analysis based on Artificial Intelligence (AI) suffers from hallucinations and issues stemming from AI alignment. To this end, this work proposes a framework for dataset risk estimation that integrates Generative AI under human guidance and supervision, aiming to set the foundations for a future automated risk analysis paradigm. Our approach utilizes LLMs to identify semantic and structural properties in database schemata, subsequently propose clustering techniques, generate the code for them and finally interpret the produced results. The human supervisor guides the model on the desired analysis and ensures process integrity and alignment with the task's objectives. A proof of concept is presented to demonstrate the feasibility of the framework's utility in producing meaningful results in risk assessment tasks.