DEAF: A Benchmark for Diagnostic Evaluation of Acoustic Faithfulness in Audio Language Models

arXiv:2603.18048 · cs.AI, cs.SD, eess.AS · Submitted 2026-03-17 · Read on arXiv

cs.AI, cs.SD, eess.AS

Submitted: 2026-03-17

Updated: 2026-10-09

Terminology

• Benchmark — 4× in this paper · explained in 2 episodes
• Diagnostic Evaluation of Acoustic Faithfulness — 2× in this paper
• Sycophancy — 1× in this paper · explained in 4 episodes

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems