“Confidence-Aware Aggregation for Multimodal Audio Reasoning” (2026), by Michel Olvera et al. Computer Science research paper. Original abstract below, unchanged. A free PDF is available.

Confidence-Aware Aggregation for Multimodal Audio Reasoning

Michel Olvera, Paraskevas Stamatiadis, Ga{ë}l Richard · November 3, 2026 · Computer Science

Abstract

Large Audio Language Models (LALMs) enable generative reasoning over complex acoustic scenes but often exhibit prediction instability. We show that this variability can serve as a reliability metric via inference-time self-consistency and confidence-aware aggregation. Using a log-probability--based scoring framework, candidate answers are weighted by model likelihoods, leveraging reasoning diversity and self-certainty without additional training. Experiments on four LALMs, including Qwen3-Omni and Audio Flamingo 3, demonstrate that confidence-aware aggregation improves accuracy and calibration, with additive methods like Borda voting outperforming classical Majority Vote, especially under high disagreement. This approach transforms LALM variability into a source of reliability for scalable and robust multimodal audio understanding. Project code is available at https://github.com/michelolzam/lalm-self-consistency.

Free PDF DOI: 10.48550/arxiv.2611.04580