A pair of language models, one acting as scammer and one as target, can simulate realistic scam conversations, but the paper presents no user evaluation of whether this improves scam resilience.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.HC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Promoting Online Safety by Simulating Unsafe Conversations with LLMs
A pair of language models, one acting as scammer and one as target, can simulate realistic scam conversations, but the paper presents no user evaluation of whether this improves scam resilience.