When Models Listen but Stop Thinking: Teaching Audio Models to Reason Like They Read
A voice assistant can transcribe your question correctly and still answer like it heard something else. That is the awkward part of modern audio-language models. The obvious diagnosis is usually “better speech recognition.” The less obvious diagnosis is nastier: the model may receive an audio input that is semantically equivalent to the text prompt, but once generation begins, its audio-conditioned reasoning trajectory drifts away from the reasoning trajectory it would have followed if the same question had been typed. ...