← Search

Baolin Li

2 accepted papers

2024

Sprout: Green Generative AI with Carbon-Efficient LLM Inference

EMNLP 2024main

The rapid advancement of generative AI has heightened environmental concerns, particularly regarding carbon emissions. Our framework, Sprout, addresses these challenges by reducing the carbon footprint of inference in large language models (LLMs). Sprout introduces “generation directives” to guide t…

2022

Great Power, Great Responsibility: Recommendations for Reducing Energy for Training Language Models

NAACL 2022findings

The energy requirements of current natural language processing models continue to grow at a rapid, unsustainable pace. Recent works highlighting this problem conclude there is an urgent need for methods that reduce the energy needs of NLP and machine learning more broadly. In this article, we invest…