Arabic Mini-ClimateGPT : A Climate Change and Sustainability Tailored Arabic LLM
Submission Type: Regular Short Paper
Submission Track: NLP Applications
Submission Track 2: Theme Track: Large Language Models and the Future of NLP
Keywords: Large Language Model, Climate change, Sustainability, Arabic NLP
TL;DR: An Open-source Climate change and Sustainability Tailored Arabic LLM
Abstract: Climate change is one of the most significant challenges we face together as a society. Creating awareness and educating policy makers the wide-ranging impact of climate change is an essential step towards a sustainable future. Recently, Large Language Models (LLMs) like ChatGPT and Bard have shown impressive conversational abilities and excel in a wide variety of NLP tasks. While these models are close-source, recently alternative open-source LLMs such as Stanford Alpaca and Vicuna have shown promising results. However, these open-source models are not specifically tailored for climate related domain specific information and also struggle to generate meaningful responses in other languages such as, Arabic. To this end, we propose a light-weight Arabic Mini-ClimateGPT that is built on an open-source LLM and is specifically fine-tuned on a conversational-style instruction tuning curated Arabic dataset Clima500-Instruct with over 500k instructions about climate change and sustainability. Further, our model also utilizes a vector embedding based retrieval mechanism during inference. We validate our proposed model through quantitative and qualitative evaluations on climate-related queries. Our model surpasses the baseline LLM in 88.3% of cases during ChatGPT-based evaluation. Furthermore, our human expert evaluation reveals an 81.6% preference for our model's responses over multiple popular open-source models. Our open-source demos, models and curated instruction sets are available here : https://github.com/mbzuai-oryx/ClimateGPT
Submission Number: 1906
Loading