Selective Capability Unlearning in End-to-End Spoken Language Understanding

The article introduces a novel framework called Binding Subspace (BSU) for selective capability unlearning in end-to-end spoken language understanding (SLU) systems. BSU addresses the issue of capability persistence, where autoregressive models fail to fully suppress specific intents due to their conditional mapping behavior, by isolating and attenuating intent-conditioned representations. This approach significantly reduces the recoverability of suppressed intents while maintaining performance on SLU benchmarks, which is crucial for practitioners needing to comply with safety and policy constraints in deployed systems.