Information Extraction from Electricity Invoices with General-Purpose Large Language Models
For enterprises needing to automate information extraction from semi-structured business documents, this work provides an empirical framework showing that prompt engineering is the critical lever for maximizing LLM-based extraction fidelity.
This study evaluates general-purpose LLMs (Gemini 1.5 Pro and Mistral-small) for extracting structured information from Spanish electricity invoices without fine-tuning, achieving up to 97.61% F1-score with few-shot prompting. Prompt quality dominates over hyperparameter tuning, with a 19+ percentage point gap between zero-shot and best few-shot strategies.
Information extraction from semi-structured business documents remains a critical challenge for enterprise management. This study evaluates the capability of general-purpose Large Language Models to extract structured information from Spanish electricity invoices without task-specific fine-tuning. Using a subset of the IDSEM dataset, we benchmark two architecturally distinct models, Gemini 1.5 Pro and Mistral-small, across 19 parameter configurations and 6 prompting strategies. Our experimental framework treats prompt engineering as the primary experimental variable, comparing zero-shot baselines against increasingly sophisticated few-shot approaches and iterative extraction strategies. Results demonstrate that prompt quality dominates over hyperparameter tuning: the F1-score variation across all parameter configurations is marginal, while the gap between zero-shot and the best few-shot strategy exceeds 19 percentage points. The best configuration (few-shot with cross-validation) achieves an F1-score of 97.61% for Gemini and 96.11% for Mistral-small, with document template structure emerging as the primary determinant of extraction difficulty. These findings establish that prompt design is the critical lever for maximizing extraction fidelity in LLM-based document processing, thereby providing an empirical framework for integrating general-purpose LLMs into business document automation.