2 papers
cs.MM2026
Causal Localization of the Refusal Direction in Audio Language Models
Leonardo Haw-Yang Foo, Hung-yi Lee
A large audio language model (LALM) attaches a speech front end to a text language model (LM) that is already safety-aligned. When such a model refuses a harmful spoken request, is…
cs.SD2026
All That Glitters Is Not Audio: Rethinking Text Priors and Audio Reliance in Audio-Language Evaluation
Leonardo Haw-Yang Foo, Chih-Kai Yang, Chen-An Li +2
Large Audio-Language Models show consistent performance gains across speech and audio benchmarks, yet high scores may not reflect true auditory perception. If a model can answer qu…