A systematic evaluation shows GPT-4o and GPT-4 outperform open-source LLMs on crisis tweet classification, with flood events and urgent-need messages as consistent failure points.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Evaluating Robustness of LLMs on Crisis-Related Microblogs across Events, Information Types, and Linguistic Features
A systematic evaluation shows GPT-4o and GPT-4 outperform open-source LLMs on crisis tweet classification, with flood events and urgent-need messages as consistent failure points.