mlsanityData to 14 Oct 2026

ALLM4ADD: Unlocking the Capabilities of Audio Large Language Models for Audio Deepfake Detection

arXiv 2505.11079 ↗First posted 16 May 2025cs.SD cs.CL eess.AScited by 17

Not on the map. Why?

Abstract (arXiv)

Audio deepfake detection (ADD) has grown increasingly important due to the rise of high-fidelity audio generative models and their potential for misuse. Given that audio large language models (ALLMs) have made significant progress in various audio processing tasks, a heuristic question arises: textitCan ALLMs be leveraged to solve ADD?. In this paper, we first conduct a comprehensive zero-shot evaluation of ALLMs on ADD, revealing their ineffectiveness. To this end, we propose ALLM4ADD, an ALLM-driven framework for ADD. Specifically, we reformulate ADD task as an audio question answering problem, prompting the model with the question: ``Is this audio fake or real?''. We then perform supervised fine-tuning to enable the ALLM to assess the authenticity of query audio. Extensive experiments are conducted to demonstrate that our ALLM-based method can achieve superior performance in fake audio detection, particularly in data-scarce scenarios. As a pioneering study, we anticipate that this work will inspire the research community to leverage ALLMs to develop more effective ADD systems. Code is available at https://github.com/ucas-hao/qwenaudioforadd.git

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 30 of its 53 references that are in the map. First posted on arXiv 16 May 2025.

Builds on

30 of 53 references.

References · 30

  1. 2017Attention Is All You Needcited by 60,361
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  4. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  5. 2023Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understandingcited by 1,471
  6. 2023SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilitiescited by 529
  7. 2021AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networkscited by 180
  8. 2018Speaker Recognition from Raw Waveform with SincNetcited by 166
  9. 2020End-to-end anti-spoofing with RawNet2cited by 164
  10. 2023Prompting Large Language Models with Speech Recognition Abilitiescited by 140
  11. 2015A Light CNN for Deep Face Representation with Noisy Labelscited by 126
  12. 2022ADD 2022: the First Audio Deep Synthesis Detection Challengecited by 96
18 more
  1. 2020Voice Conversion Challenge 2020: Intra-lingual semi-parallel and cross-lingual voice conversioncited by 75
  2. 2021End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detectioncited by 70
  3. 2021LEAF: A Learnable Frontend for Audio Classificationcited by 69
  4. 2024Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensicscited by 69
  5. 2023ADD 2023: the Second Audio Deepfake Detection Challengecited by 64
  6. 2021ASVspoof 2019: spoofing countermeasures for the detection of synthesized, converted and replayed speechcited by 58
  7. 2024Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTScited by 54
  8. 2023Audio Deepfake Detection: A Surveycited by 50
  9. 2024X2-DFD: A framework for eXplainable and eXtendable Deepfake Detectioncited by 35
  10. 2024RawBMamba: End-to-End Bidirectional State Space Model for Audio Deepfake Detectioncited by 27
  11. 2025video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Modelcited by 24
  12. 2024I Can Hear You: Selective Robust Training for Deepfake Audio Detectioncited by 13
  13. 2025Forensics-Bench: A Comprehensive Forgery Detection Benchmark Suite for Large Vision Language Modelscited by 13
  14. 2022EmoFake: An Initial Dataset for Emotion Fake Audio Detectioncited by 10
  15. 2022SceneFake: An Initial Dataset and Benchmarks for Scene Fake Audio Detectioncited by 5
  16. 2024CLAIR-A: Leveraging Large Language Models to Judge Audio Captionscited by 5
  17. 2025Enhancing Speech Large Language Models with Prompt-Aware Mixture of Audio Encoderscited by 5
  18. 2024Utilizing Speaker Profiles for Impersonation Audio Detectioncited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 16.

17 papers.

Sort:

By area:

  1. 2025R4ec: A Reasoning, Reflection, and Refinement Framework for Recommendation Systemscited by 16
  2. 2026Interpretable All-Type Audio Deepfake Detection with Audio LLMs via Frequency-Time Reinforcement Learningcited by 6
  3. 2026Towards Explicit Acoustic Evidence Perception in Audio LLMs for Speech Deepfake Detectioncited by 5
  4. 2026WaveScat: Wavelet Scattering Front-Ends with Self-Supervised Features for Speech Deepfake Detectioncited by 3
  5. 2026Unifying Speech Editing Detection and Content Localization via Prior-Enhanced Audio LLMscited by 1
  6. 2026Leveraging large multimodal models for audio-video deepfake detection: a pilot studycited by 0
  7. 2026Probabilistic Verification of Voice Anti-Spoofing Modelscited by 0
  8. 2026Enhancing Efficiency and Performance in Deepfake Audio Detection through Neuron-level Dropin & Neuroplasticity Mechanismscited by 0
  9. 2026ICLAD: In-Context Learning with Comparison-Guidance for Audio Deepfake Detectioncited by 0
  10. 2026XAI-Grounded Explanation Generation for Speech Deepfake Detection with Training-Free Multimodal Large Language Modelscited by 0
  11. 2026Large Audio Language Models for Spoofing-Aware Speaker Verificationcited by 0
  12. 2026ToolDF: Tool-Integrated Reasoning for Mixed-Authenticity Audio Deepfake Detectioncited by 0
5 more
  1. 2026CRAF: Cross-View Residual-Aware Fusion for Deepfake Speech Detectioncited by 0
  2. 2026Spooftral: Can Voxtral Audio-Language Model Detect Speech Spoofing?cited by 0
  3. 2026GLAD: Global-Local Adaptive Detector for Robust Speech Deepfake Detectioncited by 0
  4. 2026SE-ADD: Self-Evolving Audio Deepfake Detection with Mistake-Driven Supervisioncited by 0
  5. 2026SEAR: Spoofing Evidence-Grounded Audio Reasoning Benchmark for Audio Language Modelscited by 0