BIRDS: Characterizing and Understanding Biodiversity Impact of Large Language Model Serving

Abstract:Large language model (LLM) serving creates environmental impacts beyond carbon and water, including ecosystem damage through biodiversity-related pathways. We present BIRDS, a framework for Biodiversity Impact of Request-Driven LLM Serving. BIRDS defines request-level functional units, quantifies operational and embodied biodiversity impact, and introduces Quality-Normalized Biodiversity Impact (QNBI) to jointly analyze ecological impact and response quality. Across diverse workloads, models, GPUs, and regions, BIRDS reveals that biodiversity impact accumulates at scale and exposes quality-aware serving tradeoffs. The code is available at this https URL.

Other Quantitative Biology (q-bio.OT); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)

arXiv:2605.27480 [q-bio.OT]

(or arXiv:2605.27480v3 [q-bio.OT] for this version)

https://doi.org/10.48550/arXiv.2605.27480 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.