Hyebin Cho
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Sound×1
Frequent co-authors
Research Timeline
2026
Who Wins the Conflict? Mechanistic Interpretability of Text Bias in Audio LLMs
This paper investigates the text dominance phenomenon in Audio Large Language Models and proposes a training-free intervention to reduce it.
Highlighted terms show continued research focus across papers
Papers
cs.SDEmpiricalRecentJun 17, 2026
Who Wins the Conflict? Mechanistic Interpretability of Text Bias in Audio LLMs
Hyebin Cho, Suho Yoo, Jaehyuk Jang, Changick Kim +1 more
This paper investigates the text dominance phenomenon in Audio Large Language Models and proposes a training-free intervention to reduce it.
View →