SEAR: Spoofing Evidence-Grounded Audio Reasoning Benchmark for Audio Language Models
TL;DR
Spoofing evidence-grounded audio reasoning is introduced, a four-task AQA benchmark to evaluate ALM-based ADD through acoustic evidence identification and quantification, deepfake detection, and forensic rationale generation, and a bona-fide-based acoustic evidence agent (BAEA), which equips a frozen ALM with controlled acoustic tools under \textsc{fixed} or \textsc{adaptive} evidence-acquisition policies.
Abstract
Audio language models (ALMs) are increasingly used for audio deepfake detection (ADD), yet existing benchmarks assess their verdicts or rationale plausibility without verifying the underlying acoustic evidence. To address this issue, we first introduce spoofing evidence-grounded audio reasoning (SEAR), a four-task AQA benchmark to evaluate ALM-based ADD through acoustic evidence identification and quantification, deepfake detection, and forensic rationale generation. We further propose a bona-fide-based acoustic evidence agent (BAEA), which equips a frozen ALM with controlled acoustic tools under \textsc{fixed} or \textsc{adaptive} evidence-acquisition policies. Experiments with six ALMs reveal a clear gap between plausible rationales and verifiable acoustic evidence reasoning, while BAEA-\textsc{Fixed} improves final verdicts and forensic rationales on both evaluation partitions. Controlled interventions further show that misleading evidence degrades both detection and grounding performance.
