LLM Digest

Story

arxiv_cs_ai · Jun 24, 2026 · paper

Source brief

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

arxiv.orgJun 24, 2026
original source linked

In brief

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...

Feed lens

eval

Read the original at arxiv.org →Open in live feed Read that day’s brief

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

Earlier in this thread 4 items

Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelity

CORTIS: Text-Only Adaptation of Spoken Language Models for Task-Oriented Voice Agents

Article: Understanding ML Model Poisoning: How It Happens and How to Detect It

MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism