量化大模型服务对生物多样性的隐性影响，揭示质量与生态的权衡。
BIRDS: Characterizing and Understanding Biodiversity Impact of Large Language Model Serving
- 构建请求级框架，区分运行与制造阶段的生物多样性影响。
- 发现大规模服务下生物多样性影响显著累积，且随性能提升而加剧。
- 提出质量归一化指标，适合关注绿色AI的系统设计者使用。
大语言模型（LLM）服务带来的环境影响不仅限于碳排放和用水，还通过与生物多样性相关的路径造成生态系统损害。我们提出BIRDS框架，用于评估请求驱动型LLM服务的生物多样性影响。BIRDS定义了请求级别的功能单元，量化了运行与嵌入式生物多样性影响，并引入质量归一化生物多样性影响（QNBI）指标，以联合分析生态影响与响应质量。在多种工作负载、模型、GPU及地区环境下，BIRDS揭示了生物多样性影响随规模累积的现象，并暴露了质量感知服务中的权衡关系。代码已开源：https://github.com/TianyaoShi/BIRDS。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。