Enhancing Audio Reasoning via Semantic Summary Prediction
Large Audio Language Models (LALMs) perform well on complex question answering but often show a reasoning gap, where explicit Chain-of-Thought (CoT) reduces accuracy compared to direct answers. We hypothesize that long reasoning sequences shift attention away from the audio input. To address this, we propose SPARE (Sem...
Francesco Bonzi, Pooneh Mousavi, Cem Subakan et al.
· 1 citation