Carbon Footprint Accounting Driven by Large Language Models and Retrieval-Augmented Generation
Carbon footprint accounting (CFA) is critical for decarbonization efforts but remains constrained by static databases, fragmented data sources, and labor-intensive expert workflows. Conventional life cycle assessment (LCA) methods struggle to adapt to dynamic production changes, policy updates, and enterprise-specific data privacy requirements. While large language models (LLMs) offer promising automation capabilities, no practical frameworks currently exist for fully automated CFA; directly applying LLMs introduces limitations such as weak factual grounding, poor responsiveness, high inference costs, and insufficient handling of confidential data. To address these gaps, this paper proposes LLMs-RAG-CFA, a unified framework that combines large language models with retrieval-augmented generation (RAG) to deliver real-time, reliable, cost-efficient, and privacy-preserving CFA. The system incorporates semantic segmentation, top-k domain-specific fragment retrieval, uncertainty-aware and input-length-aware prompt construction strategies to optimize real-time professional coverage, reduce uncertainty and reduce token consumption. Interval-based uncertainty metrics are designed to quantify retrievaland accounting-stage uncertainty, supporting more interpretable and trustworthy carbon assessments. Extensive experiments across five carbon-intensive industries (primary aluminum, lithium batteries, photovoltaics, new energy vehicles, and transformers) demonstrate that LLMs-RAG-CFA consistently outperforms baseline CFA workflows by achieving higher retrieval completeness, lower information deviation, and lower accounting deviation. A complete set of analysis covering real-time adaptability, cost trade-offs, and privacy handling further supports its practical viability. This framework offers a scalable, practical pathway for real-time carbon emission monitoring and supports improved sustainability practices.