SFL-MTSC improves slot F1 and overall accuracy in zero-shot multi-intent SLU on MAC-SLU by decomposing predictions into intent-specific frames, applying domain-intent grouping and slot clustering, and retaining reliable frames via path support scoring.
SFL-MTSC: Leveraging Semantic Frame-Level Multi-Task Self-Consistency for Robust Multi-Intent Spoken Language Understanding
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Prompt-based spoken language understanding (SLU) with large language models (LLMs) often suffers from inconsistent intent--slot structures due to decoding stochasticity, particularly in multi-intent scenarios. In view of this, we propose Semantic Frame-Level Multi-Task Self-Consistency (SFL-MTSC), a novel structured aggregation framework operating at the semantic frame level. Instead of output-level majority voting, SFL-MTSC decomposes predictions into intent-specific frames, applies domain--intent grouping and slot-level clustering, and evaluates cluster reliability using path support scoring. Reliable frames are retained and re-integrated to form the final prediction. Zero-shot experiments on the MAC-SLU benchmark dataset show improved slot F1 and overall accuracy over single-path inference, while intent accuracy remains largely stable across most settings.
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SFL-MTSC: Leveraging Semantic Frame-Level Multi-Task Self-Consistency for Robust Multi-Intent Spoken Language Understanding
SFL-MTSC improves slot F1 and overall accuracy in zero-shot multi-intent SLU on MAC-SLU by decomposing predictions into intent-specific frames, applying domain-intent grouping and slot clustering, and retaining reliable frames via path support scoring.