MisBench provides a 10.3M-example benchmark of styled, conflict-based misinformation and shows LLMs' detection accuracy depends strongly on conflict type and textual style.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
How does Misinformation Affect Large Language Model Behaviors and Preferences?
MisBench provides a 10.3M-example benchmark of styled, conflict-based misinformation and shows LLMs' detection accuracy depends strongly on conflict type and textual style.