HalluAudio: A Comprehensive Benchmark for Hallucination Detection in Large Audio-Language Models

ArXi:2604.19300v1 Announce Type: cross Large Audio-Language Models (LALMs) have recently achieved strong performance across various audio-centric tasks. However, hallucination, where models generate responses that are semantically incorrect or acoustically uned, remains largely underexplored in the audio domain. Existing hallucination benchmarks mainly focus on text or vision, while the few audio-oriented studies are limited in scale, modality coverage, and diagnostic depth. We therefore