The paper introduces an uncertainty-aware LLM pipeline for crisis reporting that classifies social media situational claims and evaluates their plausibility using external proxy data to produce reports that include confidence levels.
Just ask for calibration: Strategies for eliciting calibrated confidence scores from language models fine- tuned with human feedback
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LLM-based uncertainty assessment of social media situational signals for crisis reporting
The paper introduces an uncertainty-aware LLM pipeline for crisis reporting that classifies social media situational claims and evaluates their plausibility using external proxy data to produce reports that include confidence levels.