Abstract

Methods, systems, and computer program products are provided for extracting data from a data file using a large language model. An example method includes: receiving a first data file having first data in a first format; inputting the first data file and a prompt to a non-deterministic LLM; executing, with the LLM, the prompt a plurality of separate times, thereby generating a plurality of separate output files based on the input file; comparing the plurality of output files to generate a score representing a similarity of the plurality of output files; in response to the score satisfying a threshold, generating a final output file including the plurality of first data from the first data file in the second format; and automatically populating fields of a database with the plurality of first data in the second format from the final output file.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.

Share

COinS