CarbonPDF: Question-Answering Reasoning Framework for Assessing Product Carbon Footprint in PDF Documents
Abstract: Product sustainability reports provide valuable insights into the environmental impacts of a product and are often distributed in PDF format. These reports often include a combination of tables and text, which complicates their analysis. The lack of standardization and the variability in reporting formats further exacerbate the difficulty of extracting and interpreting relevant information from large volumes of documents. In this paper, we tackle the challenge of answering questions related to carbon footprints within sustainability reports available in PDF format. Unlike previous approaches, our focus is on addressing the difficulties posed by the unstructured and inconsistent nature of text extracted from PDF parsing. To facilitate this analysis, we introduce CarbonPDF-QA, an open-source dataset containing question-answering pairs for each document, along with human-annotated answers. Our evaluation of GPT-4 on this dataset reveals its inadequacy in answering questions based on inconsistent data. To address this limitation, we propose CarbonPDF, an LLM-based technique specifically designed to answer carbon footprint questions on such datasets. We develop CarbonPDF by fine-tuning Llama 3 with our training data. Our results show that our technique outperforms current state-of-the-art techniques, including question-answering (QA) systems finetuned on table and text data.
Paper Type: Long
Research Area: Question Answering
Research Area Keywords: Question Answering, Generation, Language Modeling,NLP Applications,Resources and Evaluation
Contribution Types: Data resources, Data analysis
Languages Studied: English
Submission Number: 262
Loading