Val-LLM: A Visual Analytics Approach for the Critical Validation of LLM-Generated Tabular Data

Large Language Models (LLMs) are emerging as promising approaches for tabular data generation and enrichment, helping to ease constraints related to data availability. However, the reliable use of LLM-generated data remains challenging, e.g., due to hallucinations and inconsistencies. While some validation approaches exist, five key challenges remain: the lack of explanations and transparency in how values are generated, balancing fine-grained accurate with coarse-grained scalable validation, validating generated data without ground truth, and evaluating plausibility, semantic relevance, and downstream utility. To address these challenges, we present Val-LLM, a novel visual analytics approach for the critical validation of LLM-generated tabular data. Val-LLM enables users to contextualize generated data values with explanations, externalize human expert knowledge, relate LLM outputs with existing data, and assess the data utility in an application downstream. We conducted a user study to evaluate Val-LLM. Results highlight the usefulness of supporting multiple levels of granularity and enabling human knowledge externalization for validation. The study also indicates the need to study validation workflows and workflow flexibility, based on user domain experience and user preferences. Our work supports the trustworthy and effective use of LLM-generated tabular data by integrating visual analytics for systematic data validation.