SEAR: Spoofing Evidence-Grounded Audio Reasoning Benchmark for Audio Language Models
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 controlle...