Summary of Crisissense-llm: Instruction Fine-tuned Large Language Model For Multi-label Social Media Text Classification in Disaster Informatics, by Kai Yin et al.
CrisisSense-LLM: Instruction Fine-Tuned Large Language Model for Multi-label Social Media Text Classification in Disaster Informatics
by Kai Yin, Chengkai Liu, Ali Mostafavi, Xia Hu
First submitted to arxiv on: 16 Jun 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper presents a novel approach to improving situational awareness in disasters by developing a Large Language Model (LLM) capable of multi-label classification of disaster-related tweets. The authors enhance a pre-trained LLM through instruction fine-tuning, creating a comprehensive dataset from disaster-related tweets and using it to fine-tune the model with disaster-specific knowledge. This approach allows for simultaneous categorization of multiple aspects of disaster-related information, such as event type, informativeness, and human aid involvement, significantly improving social media data utility for situational awareness in disasters. The results demonstrate enhanced categorization of critical information from social media posts, facilitating effective deployment for situational awareness during emergencies. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper creates a new way to analyze tweets about disasters. It uses a special kind of computer model that can understand what people are saying online during emergencies. This model is trained on lots of examples of disaster-related tweets and can identify different types of information, like what kind of event happened or if people are helping each other. This helps emergency responders get a better picture of what’s happening during disasters, which can make their responses more effective. |
Keywords
» Artificial intelligence » Classification » Fine tuning » Large language model
