Beyond Answer Changes: Matched Same-Class Controls for Local Audio Evidence

Yunuo Wang, Maoyuan Chen, Yuanjin Huang, Xing Liu|October 27, 2026arXiv

Key Takeaway

To properly evaluate audio-language model robustness, use matched same-class sound replacements as a control—this isolates whether answer changes reflect genuine understanding of sound events versus sensitivity to waveform artifacts.

Summary

This paper introduces a method to test how audio-language models respond to local sound changes by comparing what happens when you replace a sound event with another from the same class versus a different class.

evaluation multimodal safety

Key Terms

audio-language-model local-audio-evidence matched-control soundscape