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 https://github.com/TianyaoShi/BIRDS.

23 pages, 27 figures, 10 tables, the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP), Budapest, Hungary, October 24-29th, 2026