cs.SDNov 3, 2026

Confidence-Aware Aggregation for Multimodal Audio Reasoning

Authors: Michel Olvera, Paraskevas Stamatiadis, Ga{ë}l Richard

Organizations: S2A, LTCI, IDS · S2A, IDS

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.

Explore similar work

CardsList
  1. Multi-Source Evidence Fusion for Audio Question Answering

    Mar 18, 2026Aivo Olev, Tanel AlumäeAudio QAAudio Reasoning

  2. Beyond Accuracy: ARIA-Rubrics for Evaluating Audio Reasoning in Large Audio Language Models

    Sep 9, 2026Yupei Li, Qiyang Sun, Mohamed Mady +4Audio-Language Model EvaluationAudio Reasoning

  3. ALARM: Audio-Language Alignment for Reasoning Models

    Mar 10, 2026Petr Grinberg, Hassan ShahmohammadiAudio-Language ModelsAudio Reasoning