AVLLMs encode audio semantics in middle layers but suppress them in final text outputs when audio conflicts with vision, due to training that largely inherits from vision-language base models.
Audiolens: A closer look at auditory attribute percep- tion of large audio-language models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Audio-language models retain 60-72% of benchmark scores without audio, and most audio-dependent items can be solved from short fragments rather than full clips.
citing papers explorer
-
Do Audio-Visual Large Language Models Really See and Hear?
AVLLMs encode audio semantics in middle layers but suppress them in final text outputs when audio conflicts with vision, due to training that largely inherits from vision-language base models.
-
All That Glitters Is Not Audio: Rethinking Text Priors and Audio Reliance in Audio-Language Evaluation
Audio-language models retain 60-72% of benchmark scores without audio, and most audio-dependent items can be solved from short fragments rather than full clips.