๐Ÿ“–
SKAD: Sketch-Guided Audio-Contrastive Decoding for Reasoning in Large Audio-Language Models
Junyu Wang, Peiyuan Jiang, Siyuan Zhang, Jian Zong, Tianrui Wang, Zikang Huang, Meng Ge, Longbiao Wang, Jianwu Dang

SKAD: Sketch-Guided Audio-Contrastive Decoding for Reasoning in Large Audio-Language Models

Science & Mathematics Published 2026 Verification Pending

Overview & Synopsis

Large Audio-Language Models (LALMs) have shown increasing potential in audio understanding and reasoning by generating intermediate reasoning steps before answering. However, directly eliciting long-form reasoning from audio does not always lead to more reliable predictions. Even reasoning-oriented LALMs may gradually shift from acoustic evidence to language-continuation patterns during generation. A natural solution is to use contrastive decoding with an audio-masked branch, but directly applying this strategy to plain chain-of-thought reasoning is often ineffective, since the masked branch lacks sufficient audio-related context and provides an unstable reference. To address this issue, we propose \textbf{SKAD} (\textbf{Sk}etch-Guided \textbf{A}udio-Contrastive \textbf{D}ecoding), a training-free inference-time method for audio reasoning. SKAD first constructs an acoustic evidence sketch that summarizes question-relevant auditory information. It then performs contrastive decoding between an audio-conditioned reasoning branch and a sketch-only branch. By using the sketch as a shared semantic scaffold, SKAD makes the masked branch more informative and encourages decoding decisions that are more dependent on the original audio. We evaluate SKAD on Qwen2.5-Omni-7B and Step-Audio-R1 across three audio understanding and reasoning benchmarks: MMAR, MMAU, and MMSU. Experimental results show that SKAD consistently improves the average accuracy of both models across all benchmarks. Further ablations show that direct contrastive decoding without the acoustic evidence sketch provides limited or negative gains, confirming the importance of constructing a reliable contrastive reference before audio-contrastive decoding.

Indexed from repository: arXiv (arxiv.org)
Loading document from verified source...
Keyboard Shortcuts: ← / → for pages • + / - for zoom • 0 to fit width Powered by Mozilla PDF.js v3.11

Document Information

Document Title SKAD: Sketch-Guided Audio-Contrastive Decoding for Reasoning in Large Audio-Language Models
Author / Organization Junyu Wang, Peiyuan Jiang, Siyuan Zhang, Jian Zong, Tianrui Wang, Zikang Huang, Meng Ge, Longbiao Wang, Jianwu Dang
Subject & Discipline eess.AS
Categories Science & Mathematics
Publication Year 2026
License / Rights arXiv Open Access / Creative Commons
Resource Verification Listed PDF (Verification Pending)
Original Host Website arXiv (arxiv.org)
File Format application/pdf (Portable Document Format)
Language EN
Catalog ID DOC-269973
Original Source Link Visit Source Page on arxiv.org »