mlsanityData to 7 Oct 2026

SEALing the Gap: A Reference Framework for LLM Inference Carbon Estimation via Multi-Benchmark Driven Embodiment

arXiv 2603.02949 ↗First posted 3 Mar 2026cs.SE cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Large Language Models are rapidly gaining traction in software engineering, yet their growing carbon footprint raises pressing sustainability concerns. While training emissions are substantial, inference quickly surpasses them due to the sheer volume of prompts processed. This shift underscores the urgent need for accurate, prompt-level carbon measurement during inference to enable informed, sustainability-focused decision-making. To address the limitations of existing approaches, in this paper, we outline the guiding principles for a novel reference framework for LLM inference carbon estimation that can guide the design of future tools and provide a systematic foundation for advancing sustainability research in this domain. We also introduce SEAL, an early embodiment of these principles that leverages a multi-benchmark-driven approach for per-prompt carbon estimation. Its initial validation shows promising results, positioning SEAL as a foundation for standardized sustainability assessment across the LLM ecosystem.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 10 of its 24 references that are in the map. First posted on arXiv 3 Mar 2026.

Builds on

10 of 24 references.

References · 10

  1. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  2. 2020Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learningcited by 246
  3. 2021Compute and Energy Consumption Trends in Deep Learning Inferencecited by 61
  4. 2025Energy Considerations of Large Language Model Inference and Efficiency Optimizationscited by 54
  5. 2024Offline Energy-Optimal LLM Serving: Workload-Based Energy Models for LLM Inference on Heterogeneous Systemscited by 27
  6. 2024The Price of Prompting: Profiling Energy Use in Large Language Models Inferencecited by 22
  7. 2024LLMCO2: Advancing Accurate Carbon Footprint Prediction for LLM Inferencescited by 19
  8. 2025Quantifying the Energy Consumption and Carbon Emissions of LLM Inference via Simulationscited by 12
  9. 2025Brevity is the soul of sustainability: Characterizing LLM response lengthscited by 9
  10. 2022ESAVE: Estimating Server and Virtual Machine Energycited by 1

Built on by

Not cited yet.