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

• URL: http://arxiv.org/abs/2605.27480v2
• Date: Thu, 28 May 2026 02:27:06 GMT
• Title: BIRDS: Characterizing and Understanding Biodiversity Impact of Large Language Model Serving
• Abstract summary: BIRDS is a framework for Biodiversity Impact of Request-Driven LLM Serving.<n>It defines request-level functional units, quantifies operational and embodied biodiversity impact, and introduces Quality-Normalized Biodiversity Impact.
• Score: 5.1094466593178325
• License: http://creativecommons.org/licenses/by/4.0/
• 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 actionable quality-aware serving tradeoffs.

Related papers

• Modeling Dependency-Propagated Ecosystem Impact of Changes in Maintenance Activities: Evaluating Support Strategies in the PyPI Network [83.16077040470975]
  We introduce a dependency-aware model of ecosystem impact that captures how changes in maintenance activities propagate through the Python Package Index (PyPI) ecosystem.<n>Our results show that a large share of the modeled ecosystem impact can be attributed to just 0.1% of all PyPI packages when prioritized based on dependency-propagated impact.
  arXiv  Detail & Related papers  (2026-05-07T12:51:00Z)
• BioAnalyst: A Foundation Model for Biodiversity [0.565395466029518]
  We introduce BioAnalyst, the first Foundation Model tailored for biodiversity analysis and conservation planning.<n>BioAnalyst employs a transformer-based architecture, pretrained on extensive multi-modal datasets.<n>We evaluate the model's performance on two downstream use cases, demonstrating its generalisability compared to existing methods.
  arXiv  Detail & Related papers  (2025-07-11T23:56:08Z)
• When Servers Meet Species: A Fab-to-Grave Lens on Computing's Biodiversity Impact [2.664633466640672]
  This paper presents the first end-to-end analysis of biodiversity impact from computing systems.<n>We introduce two new metrics--Embodied Biodiversity Index (EBI) and Operational Biodiversity Index (OBI)--to quantify biodiversity impact across the lifecycle.<n>We present FABRIC, a modeling framework that links computing workloads to biodiversity impacts.
  arXiv  Detail & Related papers  (2025-06-25T13:50:04Z)
• BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning [60.80381372245902]
  We find emergent behaviors in biological vision models via large-scale contrastive vision-language training.<n>We train BioCLIP 2 on TreeOfLife-200M to distinguish different species.<n>We identify emergent properties in the learned embedding space of BioCLIP 2.
  arXiv  Detail & Related papers  (2025-05-29T17:48:20Z)
• BioCube: A Multimodal Dataset for Biodiversity Research [0.31498833540989407]
  We introduce BioCube, a fine-grained global dataset for ecology and biodiversity research.<n>BioCube incorporates species observations through images, audio recordings and descriptions, environmental DNA, vegetation indices, agricultural, forest, land indicators, and high-resolution climate variables.
  arXiv  Detail & Related papers  (2025-05-16T09:46:08Z)
• BioMaze: Benchmarking and Enhancing Large Language Models for Biological Pathway Reasoning [49.487327661584686]
  We introduce BioMaze, a dataset with 5.1K complex pathway problems from real research.<n>Our evaluation of methods such as CoT and graph-augmented reasoning, shows that LLMs struggle with pathway reasoning.<n>To address this, we propose PathSeeker, an LLM agent that enhances reasoning through interactive subgraph-based navigation.
  arXiv  Detail & Related papers  (2025-02-23T17:38:10Z)
• Large Language Models for Bioinformatics [58.892165394487414]
  This survey focuses on the evolution, classification, and distinguishing features of bioinformatics-specific language models (BioLMs)<n>We explore the wide-ranging applications of BioLMs in critical areas such as disease diagnosis, drug discovery, and vaccine development.<n>We identify key challenges and limitations inherent in BioLMs, including data privacy and security concerns, interpretability issues, biases in training data and model outputs, and domain adaptation complexities.
  arXiv  Detail & Related papers  (2025-01-10T01:43:05Z)
• DivShift: Exploring Domain-Specific Distribution Shifts in Large-Scale, Volunteer-Collected Biodiversity Datasets [0.0]
  Large-scale, volunteer-collected datasets of community-identified natural world imagery like iNaturalist have enabled marked performance gains for fine-grained visual classification of species using machine learning methods.<n>Here we introduce Diversity Shift, a framework for quantifying the effects of domain-specific distribution shifts on machine learning model performance.<n>To diagnose the performance effects of biases specific to volunteer-collected biodiversity data, we also introduce DivShift - North American West Coast (DivShift-NAWC), a curated dataset of almost 7.5 million iNaturalist images across the western coast of North America partitioned across five types of expert-verified bias.
  arXiv  Detail & Related papers  (2024-10-17T23:56:30Z)
• An Evaluation of Large Language Models in Bioinformatics Research [52.100233156012756]
  We study the performance of large language models (LLMs) on a wide spectrum of crucial bioinformatics tasks. These tasks include the identification of potential coding regions, extraction of named entities for genes and proteins, detection of antimicrobial and anti-cancer peptides, molecular optimization, and resolution of educational bioinformatics problems. Our findings indicate that, given appropriate prompts, LLMs like GPT variants can successfully handle most of these tasks.
  arXiv  Detail & Related papers  (2024-02-21T11:27:31Z)
• FREE: The Foundational Semantic Recognition for Modeling Environmental Ecosystems [56.0640340392818]
  We introduce a framework, FREE, that enables the use of varying features and available information to train a universal model.<n>The core idea is to map available environmental data into a text space and then convert the traditional predictive modeling task in environmental science to a semantic recognition problem.<n>Our evaluation on two societally important real-world applications, stream water temperature prediction and crop yield prediction, demonstrates the superiority of FREE over multiple baselines.
  arXiv  Detail & Related papers  (2023-11-17T00:53:09Z)
• Ensembles of Vision Transformers as a New Paradigm for Automated Classification in Ecology [0.0]
  We show that ensembles of Data-efficient image Transformers (DeiTs) significantly outperform the previous state of the art (SOTA) On all the data sets we test, we achieve a new SOTA, with a reduction of the error with respect to the previous SOTA ranging from 18.48% to 87.50%.
  arXiv  Detail & Related papers  (2022-03-03T14:16:22Z)
• The I-ADOPT Interoperability Framework for FAIRer data descriptions of biodiversity [1.3192560874022086]
  I-ADOPT WG was formed to build a common approach to describe what is observed, measured, calculated, or derived. The I-ADOPT framework defines a set of high level semantic components that can be used to describe a variety of patterns commonly found in scientific observations. This contribution will focus on how the I-ADOPT framework can be applied to represent variables commonly used in the biodiversity domain.
  arXiv  Detail & Related papers  (2021-07-14T08:30:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.