Transparent Screening for LLM Inference and Training Impacts

The paper presents a transparent screening framework for estimating inference and training impacts of current large language models under limited observability. The framework converts natural-language application descriptions into bounded environmental estimates and supports a comparative online observatory of current market models. Rather than claiming direct measurement for opaque proprietary services, it provides an auditable, source-linked proxy methodology designed to improve comparability, transparency, and reproducibility. The framework's methodology is based on a novel combination of natural language processing, environmental modeling, and online observatory design. The authors demonstrate the effectiveness of the framework through a case study on a popular large language model. The implications of this work are significant, as it provides a means for researchers and developers to better understand the inference and training impacts of large language models, ultimately leading to more informed decision-making and improved model development.

Source: Transparent Screening for LLM Inference and Training Impacts