article.md

Technical overview: The system retrieves the relevant pages of the uploaded report using simple search. These pages are input into a finetuned [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) language model, which outputs a JSON object containing the emission information. The system achieves an emission extraction accuracy of 65% and a source citation accuracy of 77% on the [corporate-emission-reports](https://huggingface.co/datasets/nopperl/corporate-emission-reports) dataset. Note that the model is quantized due to resource limitations.