mlsanityData to 7 Oct 2026

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

arXiv 2605.27480 ↗First posted 26 May 2026q-bio.OT cs.AI cs.CYcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 16 of its 55 references that are in the map. First posted on arXiv 26 May 2026.

Builds on

16 of 55 references.

References · 16

  1. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  2. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,758
  3. 2023LongBench: A Bilingual, Multitask Benchmark for Long Context Understandingcited by 1,378
  4. 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,258
  5. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,242
  6. 2024WildChat: 1M ChatGPT Interaction Logs in the Wildcited by 598
  7. 2023RepoBench: Benchmarking Repository-Level Code Auto-Completion Systemscited by 346
  8. 2023CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completioncited by 181
  9. 2025The ML.ENERGY Benchmark: Toward Automated Inference Energy Measurement and Optimizationcited by 31
  10. 2023Toward Sustainable HPC: Carbon Footprint Estimation and Environmental Implications of HPC Systemscited by 12
  11. 2024Towards Sustainable Large Language Model Servingcited by 12
  12. 2025Unveiling Environmental Impacts of Large Language Model Serving: A Functional Unit Viewcited by 11
4 more
  1. 2025More than Carbon: Cradle-to-Grave environmental impacts of GenAI training on the Nvidia A100 GPUcited by 10
  2. 2024A Dataset for Research on Water Sustainabilitycited by 4
  3. 2025Not All Water Consumption Is Equal: A Water Stress Weighted Metric for Sustainable Computingcited by 4
  4. 2025When Servers Meet Species: A Fab-to-Grave Lens on Computing's Biodiversity Impactcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Beyond Energy: When Sustainability Dimensions Reshape LLM Serving Decisionscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Evaluating Proactive Risk Awareness of Large Language Models
  2. 2024Large Language Models (LLMs): Deployment, Tokenomics and Sustainability
  3. 2024Harnessing multiple LLMs for Information Retrieval: A case study on Deep Learning methodologies in Biodiversity publications
  4. 2025What can large language models do for sustainable food?
  5. 2024WildfireGPT: Tailored Large Language Model for Wildfire Analysis
  6. 2025Instructor-Worker Large Language Model System for Policy Recommendation: a Case Study on Air Quality Analysis of the January 2025 Los Angeles Wildfires
  7. 2025FishNet++: Analyzing the capabilities of Multimodal Large Language Models in marine biology
  8. 2025Measuring Scientific Capabilities of Language Models with a Systems Biology Dry Lab