ACL Findings2026
ICLAD: In-Context Learning with Comparison-Guidance for Audio Deepfake Detection
Benjamin Shiue-Hal Chou, Yi Zhu, Surya Koppisetti
Abstract
Audio deepfakes pose a significant security threat, yet current state-of-the-art (SOTA) detection systems do not generalize well to realistic in-the-wild deepfakes. We introduce a novel In-Context Learning paradigm with comparison-guidance for Audio Deepfake detection (ICLAD). The framework enables the use of audio language models (ALMs) for training-free generalization to unseen deepfakes and provides textual rationales on the detection outcome. At the core of ICLAD is a pairwise comparative reasoning strategy that guides the ALM to discover and filter hallucinations and deepfake-irrelevant acoustic attributes. The ALM works alongside a specialized deepfake detector, whereby a routing mechanism feeds out-of-distribution samples to the ALM. On in-the-wild datasets, ICLAD improves macro F1 over the specialized detector, with up to 2× relative improvement. Further analysis demonstrates the flexibility of ICLAD and its potential for deployment on recent opensource ALMs.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on10
- Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
- wav2vec 2.0: A Framework for Self-Supervised Learning of Speech RepresentationsAlexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, Michael AuliNeurIPS 2020 · 9,451 citations
- Voicebox: Text-Guided Multilingual Universal Speech Generation at ScaleMatthew Le, Apoorv Vyas, Bowen Shi, Brian Karrer et al.NeurIPS 2023 · 613 citations
- Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language ModelsSreyan Ghosh, Arushi Goel, Jaehyeon Kim, Sonal Kumar et al.NeurIPS 2025 · 299 citations
- What Makes Good Examples for Visual In-Context Learning?Yuanhan Zhang, Kaiyang Zhou, Ziwei LiuNeurIPS 2023 · 219 citations
Related papers
- ALLM4ADD: Unlocking the Capabilities of Audio Large Language Models for Audio Deepfake DetectionHao Gu, Jiangyan Yi, Chenglong Wang, Jianhua Tao et al.ACM MM 2025 · 5 citations
- ALDEN: Dual-Level Disentanglement with Meta-learning for Generalizable Audio Deepfake DetectionYuxiong Xu, Bin Li, Weixiang Li, Sara Mandelli et al.ACM MM 2025
- SLIM: Style-Linguistics Mismatch Model for Generalized Audio Deepfake DetectionYi Zhu, Surya Koppisetti, Trang Tran, Gaurav BharajNeurIPS 2024 · 41 citations
- AVFF: Audio-Visual Feature Fusion for Video Deepfake DetectionTrevine Oorloff, Surya Koppisetti, Nicolò Bonettini, Divyaraj Solanki et al.CVPR 2024 · 51 citations
- ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned RepresentationQing Huang, Zhipei Xu, Xuanyu Zhang, Xiangyu Yu et al.CVPR 2026 · 3 citations
