A system trained with marketing-inspired synthetic data and curriculum learning detects embedded ads well, while classifier-guided rewriting (best-of-N and fine-tuning) makes generated ads significantly harder to detect.
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
-
TeamCMU at Touch\'e: Adversarial Co-Evolution for Advertisement Integration and Detection in Conversational Search
A system trained with marketing-inspired synthetic data and curriculum learning detects embedded ads well, while classifier-guided rewriting (best-of-N and fine-tuning) makes generated ads significantly harder to detect.