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.
On calibration of modern neural networks
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Iterative receiver algorithms for PNC relays in multi-hop UWA networks achieve low BER of 10^{-5} in simulations and superior performance in lake and sea trials compared to baselines.
MUSE applies Mamba sequential modeling to produce real-time uncertainty estimates for visual-inertial state estimation from asynchronous multimodal sensors.
citing papers explorer
-
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.
-
Iterative Receiver Processing at Relays in PNC-Enabled Multi-Hop Underwater Acoustic Networks
Iterative receiver algorithms for PNC relays in multi-hop UWA networks achieve low BER of 10^{-5} in simulations and superior performance in lake and sea trials compared to baselines.
-
MUSE: Multimodal Uncertainty Quantification of State Estimation
MUSE applies Mamba sequential modeling to produce real-time uncertainty estimates for visual-inertial state estimation from asynchronous multimodal sensors.