EcoLLM: A Novel Fine-Tuning Framework for Environmental Sustainability in Large Language Models
Year: 2024
Type: article
Abstract: The increasing reliance on artificial intelligence (AI) models, such as Large Language Models (LLMs), poses a unique challenge regarding environmental sustainability. Current LLMs prioritize performance and versatility, often neglecting the ecological impact of the solutions they generate. This paper presents a novel approach to fine-tuning LLMs to embed environmental considerations in their responses. By adjusting their training datasets and models, we enhance the likelihood of producing environmentally friendly outcomes. We observed that responses factoring in sustainability increased from 5% to over 75% post-optimization. This paper discusses our methodology, the challenges faced, and the implications for AI's role in supporting global sustainability goals.
DOI: 10.61166/elm.v2i2.70
Authors: Gagandeep Singh, Jaskaran Singh, Gourav Arora
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Climate action
Open Access status: diamond
OpenAlex ID: W4407582683