spoken-language-understanding

Tag

Cards List
#spoken-language-understanding

SFL-MTSC: Leveraging Semantic Frame-Level Multi-Task Self-Consistency for Robust Multi-Intent Spoken Language Understanding

arXiv cs.CL · 16h ago Cached

Introduces SFL-MTSC, a structured aggregation framework for robust multi-intent spoken language understanding using LLM self-consistency at the semantic frame level, showing improved slot F1 and overall accuracy on the MAC-SLU benchmark.

0 favorites 0 likes
#spoken-language-understanding

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

arXiv cs.CL · yesterday Cached

Proposes BindingSubspace (BSU), a representation-level framework that isolates and attenuates intent-conditioned directions in end-to-end spoken language understanding models to prevent capability persistence, where suppressing an intent still allows slot generation under forced prefixes. The method reduces forced-prefix recoverability while preserving retained performance on SLU benchmarks.

0 favorites 0 likes
← Back to home

Submit Feedback