CANDY, a Chinese misinformation fact-checking benchmark, shows LLMs reach only ~76% accuracy on contamination-free claims and frequently fabricate supporting evidence, while serving better as human assistants than autonomous judges.
LTCR: Long-Text Chinese Rumor Detection Dataset
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
False information can spread quickly on social media, negatively influencing the citizens' behaviors and responses to social events. To better detect all of the fake news, especially long texts which are harder to find completely, a Long-Text Chinese Rumor detection dataset named LTCR is proposed. The LTCR dataset provides a valuable resource for accurately detecting misinformation, especially in the context of complex fake news related to COVID-19. The dataset consists of 1,729 and 500 pieces of real and fake news, respectively. The average lengths of real and fake news are approximately 230 and 152 characters. We also propose \method, Salience-aware Fake News Detection Model, which achieves the highest accuracy (95.85%), fake news recall (90.91%) and F-score (90.60%) on the dataset. (https://github.com/Enderfga/DoubleCheck)
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CANDY: Benchmarking LLMs' Limitations and Assistive Potential in Chinese Misinformation Fact-Checking
CANDY, a Chinese misinformation fact-checking benchmark, shows LLMs reach only ~76% accuracy on contamination-free claims and frequently fabricate supporting evidence, while serving better as human assistants than autonomous judges.