BPL extends Rational Speech Act theory with recursion depth, prior compression, and availability sampling bounds to predict misinformation susceptibility, annotator disagreement, and differential effects of mis-, dis-, and mal-information, with competitive results on LIAR and MultiFC veracity tasks.
Our experiments show thatBPLis a good veracity classifier driven primarily by prior compression
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Cognitively Grounded Bayesian Framework for Misinformation Susceptibility
BPL extends Rational Speech Act theory with recursion depth, prior compression, and availability sampling bounds to predict misinformation susceptibility, annotator disagreement, and differential effects of mis-, dis-, and mal-information, with competitive results on LIAR and MultiFC veracity tasks.