With the rapid progress of large audio-language models (LALMs), audio question answering (AQA) has emerged as a challenging task requiring both fine-grained audio understanding and complex reasoning. While current methods mainly rely on constructing new datasets via captioning or reasoning traces, existing high-quality AQA data remains underutilized. To address this, we propose Omni-CLST, an error-aware Curriculum Learning framework with guided Selective Chain-of-Thought. The framework efficiently leverages existing high-quality dataset through two key strategies: an error-aware curriculum that organizes samples by difficulty, and a guided thought dropout mechanism that focuses reasoning on challenging cases. Experiments show that Omni-CLST achieves 73.80% on MMAU-mini and a new state of the art of 64.30% on MMAR, demonstrating robust generalization in multimodal audio-language understanding.
@article{arxiv.2509.12275,
title = {Omni-CLST: Error-aware Curriculum Learning with guided Selective chain-of-Thought for audio question answering},
author = {Jinghua Zhao and Hang Su and Lichun Fan and Zhenbo Luo and Hui Wang and Haoqin Sun and Yong Qin},
journal= {arXiv preprint arXiv:2509.12275},
year = {2025}
}
Comments
5 pages, 1 figure, 2 tables submitted to icassp, under prereview