ICLAD combines in-context learning and comparison guidance in audio language models with a routing detector to boost generalization and explanations for audio deepfake detection, achieving up to 2x F1 gains on wild data.
Reconciled_Evidence
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ICLAD: In-Context Learning with Comparison-Guidance for Audio Deepfake Detection
ICLAD combines in-context learning and comparison guidance in audio language models with a routing detector to boost generalization and explanations for audio deepfake detection, achieving up to 2x F1 gains on wild data.