LLMs fail to recognize most retracted articles from titles and abstracts alone, with over 80% error rate, but have low false positive rates on non-retracted articles.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Do Large Language Models know Which Published Articles have been Retracted?
LLMs fail to recognize most retracted articles from titles and abstracts alone, with over 80% error rate, but have low false positive rates on non-retracted articles.