Localizing and Editing Knowledge in Large Audio-Language Models

ArXi:2603.14343v1 Announce Type: new Large Audio-Language Models (LALMs) have shown strong performance in speech understanding, making speech a natural interface for accessing factual information. Yet they are trained on static corpora and may encode incorrect facts. Existing model editing methods localize and update facts in text-only LLMs, but do not account for continuous speech representations, or where knowledge is d across acoustic or language modules, or their cross-modal module.