Mechanistic tracing shows text suppresses but does not erase audio representations in late layers of Audio LLMs; back-patching reduces text dominance.
Causal tracing of audio-text fusion in 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
Semantic-level and verification-based uncertainty methods outperform token-level baselines for audio reasoning in ALLMs, but their relative performance on hallucination and unanswerable-question benchmarks is model- and task-dependent.
citing papers explorer
-
Who Wins the Conflict? Mechanistic Interpretability of Text Bias in Audio LLMs
Mechanistic tracing shows text suppresses but does not erase audio representations in late layers of Audio LLMs; back-patching reduces text dominance.
-
Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Models
Semantic-level and verification-based uncertainty methods outperform token-level baselines for audio reasoning in ALLMs, but their relative performance on hallucination and unanswerable-question benchmarks is model- and task-dependent.