Validation Accuracy: 0.247Test Accuracy: 0.274
Papers with Code · CC BY-SA 4.0
Fake News Detection
Fake News Detection is a natural language processing task that involves identifying and classifying news articles or other types of text as real or fake. The goal of fake news detection is to develop algorithms that can automatically identify and flag fake news articles, which can be used to combat misinformation and promote the dissemination of accurate information.
논문
Unpaired Accuracy: 92.0%
Weighted Accuracy: 83.08Per-class Accuracy (Agree): 43.82Per-class Accuracy (Disagree): 6.31Per-class Accuracy (Discuss): 85.68
Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Method
F1: 53.9
Weighted Accuracy: 81.23
Unpaired Accuracy: 98.5%
F1: 51.1
F1: 0.9883
Weighted Accuracy: 81.72Per-class Accuracy (Agree): 44.04Per-class Accuracy (Disagree): 6.60Per-class Accuracy (Discuss): 81.38
Weighted Accuracy: 84.60Per-class Accuracy (Agree): 88.47Per-class Accuracy (Disagree): 96.00Per-class Accuracy (Discuss): 87.70
Weighted Accuracy: 82.23Per-class Accuracy (Agree): 51.34Per-class Accuracy (Disagree): 10.33Per-class Accuracy (Discuss): 81.52
1:1 Accuracy: 91.21
Weighted Accuracy: 90.73Per-class Accuracy (Agree): 75.03Per-class Accuracy (Disagree): 63.41Per-class Accuracy (Discuss): 85.97
F1 score: 0.7741
Accuracy: 86.83%
F1: 55.8