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.
A Cognitively Grounded Bayesian Framework for Misinformation Susceptibility
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
In this (work in progress) paper, we present Bounded Pragmatic Listener (or BPL), a cognitively grounded Bayesian framework for modelling susceptibility to information disorder. BPL extends Rational Speech Act theory with three cognitively motivated bounds derived from the bounded rationality literature with a) a recursion depth bound (that emphasises working memory limits);b) a prior compression parameter (which is oriented at capturing information bottleneck); and c) an availability sample size (that operationalises importance sampling with saliency-weighted proposals). This allows us to test predictions about misinformation susceptibility, annotator disagreement, and the differential vulnerability to mis-, dis-, and mal-information as defined in the Information Disorder framework. We validate BPL on the LIAR and MultiFC benchmarks showcasing competitive veracity classification and experimental support for the depth-mismatch paradox.
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.