Wim Thiery
2024
Using LLMs to Build a Database of Climate Extreme Impacts
Ni Li
|
Shorouq Zahra
|
Mariana Brito
|
Clare Flynn
|
Olof Görnerup
|
Koffi Worou
|
Murathan Kurfali
|
Chanjuan Meng
|
Wim Thiery
|
Jakob Zscheischler
|
Gabriele Messori
|
Joakim Nivre
Proceedings of the 1st Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2024)
To better understand how extreme climate events impact society, we need to increase the availability of accurate and comprehensive information about these impacts. We propose a method for building large-scale databases of climate extreme impacts from online textual sources, using LLMs for information extraction in combination with more traditional NLP techniques to improve accuracy and consistency. We evaluate the method against a small benchmark database created by human experts and find that extraction accuracy varies for different types of information. We compare three different LLMs and find that, while the commercial GPT-4 model gives the best performance overall, the open-source models Mistral and Mixtral are competitive for some types of information.
Search
Co-authors
- Ni Li 1
- Shorouq Zahra 1
- Mariana Brito 1
- Clare Flynn 1
- Olof Görnerup 1
- show all...