# Confidence-Aware Aggregation for Multimodal Audio Reasoning

“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.

- Authors: Michel Olvera, Paraskevas Stamatiadis, Ga{ë}l Richard
- Published: November 3, 2026
- Field: Computer Science
- DOI: https://doi.org/10.48550/arxiv.2611.04580
- Free PDF: https://arxiv.org/pdf/2611.04580

## 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.

Canonical page: https://nerdi.pages.dev/paper/W7225259977
Read three real papers a day in Nerdi (iPhone): https://apps.apple.com/app/apple-store/id6813826387?pt=128757794&ct=web-paper&mt=8