ContentFuzz rewrites posts with LLM guidance from stance model confidence to flip machine labels without altering human intent, tested across four models and three datasets in two languages.
ISBN 9781450356398
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Proves tight upper and lower bounds showing that even small multiplicative perturbations (1+ε) to neighbor color counts greatly increase the price of uncertainty for reaching consensus in social graphs.
citing papers explorer
-
Content Fuzzing for Escaping Information Cocoons on Digital Social Media
ContentFuzz rewrites posts with LLM guidance from stance model confidence to flip machine labels without altering human intent, tested across four models and three datasets in two languages.
-
The Price of Uncertainty for Social Consensus
Proves tight upper and lower bounds showing that even small multiplicative perturbations (1+ε) to neighbor color counts greatly increase the price of uncertainty for reaching consensus in social graphs.